© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66241
    Prev
    Next
    INDEX
    Explanations

    prototype followed by

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

    This neuron activates on occurrences of the term “prototype,” especially when it appears in code (for example, JavaScript’s `.prototype`).

    oai_token-act-pair · o4-miniTriggered 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
     jeżeli
    -1.62
     jeśli
    -1.52
    嚷
    -1.31
     contando
    -1.30
     occaf
    -1.28
    ?"
    -1.26
     cuchara
    -1.24
     всички
    -1.23
    师傅
    -1.23
     такъ
    -1.22
    POSITIVE LOGITS
    が
    1.63
    ’
    1.63
    個人的
    1.53
    iffance
    1.45
    上品
    1.43
    清潔
    1.42
    噲
    1.41
    ,
    1.40
    '
    1.38
    髕
    1.38
    Activations Density 0.001%

    No Known Activations