© 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. 11873
    Prev
    Next
    INDEX
    Explanations

    archive addresses and lists

    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
    ciais
    -0.90
     vignette
    -0.84
     released
    -0.84
    BackStack
    -0.79
     coefficients
    -0.76
     buyer
    -0.73
     rans
    -0.73
     Coefficients
    -0.72
     injec
    -0.72
    vesse
    -0.71
    POSITIVE LOGITS
     archives
    1.16
     archive
    1.08
    archive
    1.04
    SUBSCRIBE
    1.00
    maj
    0.94
    archives
    0.94
     Archives
    0.93
    Archives
    0.93
     archival
    0.91
     Maj
    0.88
    Activations Density 0.048%

    No Known Activations