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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9811
    Prev
    Next
    INDEX
    Explanations

    package declarations

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

    This neuron activates on the letter‐sequence components of project or organization names in package (and similar) identifiers.

    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
     and
    -2.53
     stratég
    -1.53
     not
    -1.53
     or
    -1.51
     both
    -1.50
    💃
    -1.47
    をしました
    -1.47
    🥂
    -1.44
    瀟
    -1.41
    💞
    -1.41
    POSITIVE LOGITS
     ARISING
    1.45
    ꟷ
    1.42
     accentu
    1.37
    では
    1.35
    がある
    1.34
     Dinas
    1.32
     angefü
    1.30
     includ
    1.30
     tornou
    1.27
     jejich
    1.27
    Activations Density 0.034%

    No Known Activations