© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26477
    Prev
    Next
    INDEX
    Explanations

    implementation of

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on occurrences of the word “Implementation” (including its plural or variant forms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "implementation" in technical documentation and source code comments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    code comments or headers that declare an implementation, especially constructions like implementation of the … and related variants (implements, implementations).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     immense
    -1.60
    再加上
    -1.53
    感じが
    -1.48
    hline
    -1.45
     turmoil
    -1.44
     approving
    -1.38
    ConstraintMaker
    -1.38
    _
    -1.38
     {
    -1.38
     continually
    -1.37
    POSITIVE LOGITS
    𓆜
    1.88
    𖥧
    1.83
     operates
    1.64
     territoriale
    1.64
    衎
    1.63
     bedien
    1.59
    酲
    1.59
    噚
    1.56
    Ꮉ
    1.53
    ”，
    1.52
    Activations Density 0.027%

    No Known Activations