© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 11866
    Prev
    Next
    INDEX
    Explanations

    code comments and programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Khat
    -0.81
    ubation
    -0.78
     Kissinger
    -0.73
    𝟑
    -0.72
     cat
    -0.72
    Stage
    -0.72
    endregion
    -0.71
    Activation
    -0.70
     шах
    -0.69
    HX
    -0.69
    POSITIVE LOGITS
     entries
    0.76
    verbosity
    0.71
    addNew
    0.68
     patronage
    0.68
    佟
    0.66
    狭
    0.66
    Fourni
    0.65
    verket
    0.64
     wartawan
    0.64
     Hidup
    0.63
    Activations Density 0.064%

    No Known Activations