© 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. 34573
    Prev
    Next
    INDEX
    Explanations

    question starters and section headers

    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
    roids
    -0.73
    け
    -0.73
     саны
    -0.72
     seoul
    -0.71
    ffi
    -0.71
    ے
    -0.70
     Leopoldo
    -0.69
     noastre
    -0.69
     immerhin
    -0.68
     echip
    -0.68
    POSITIVE LOGITS
     cogni
    0.89
     Url
    0.85
    gand
    0.82
     Cort
    0.80
    agai
    0.79
    Cort
    0.79
     ল
    0.78
     UIC
    0.77
    VID
    0.75
    chom
    0.75
    Activations Density 0.019%

    No Known Activations