© 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. 22-GEMMASCOPE-RES-131K
    7. 36205
    Prev
    Next
    INDEX
    Explanations

    whether, what, how, why, which

    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_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
     motorista
    -1.14
    andosi
    -1.08
    ☯
    -1.05
     hObject
    -1.04
    yecto
    -1.02
     criada
    -1.01
    たびに
    -1.00
     pequ
    -0.99
    ↖
    -0.97
    🛏
    -0.95
    POSITIVE LOGITS
     how
    4.81
     what
    2.89
     why
    2.55
     whether
    2.33
     How
    2.19
    how
    2.11
     who
    1.75
     bagaimana
    1.71
    How
    1.59
     where
    1.59
    Activations Density 0.056%

    No Known Activations