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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128396
    Prev
    Next
    INDEX
    Explanations

    Q: Rost {#

    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
     granito
    -1.02
     همچنین
    -1.02
    不解
    -1.01
    Casi
    -1.01
     Nowhere
    -1.00
     terwijl
    -0.99
    他们的
    -0.98
     gord
    -0.97
     necesitaba
    -0.96
    その他の
    -0.96
    POSITIVE LOGITS
    jooq
    1.36
    RTLI
    1.13
    Due
    1.13
    setcounter
    1.11
    TProtocol
    1.08
    {\
    1.07
    aka
    1.06
    ห์
    1.05
    Instead
    1.05
    Why
    1.05
    Activations Density 0.000%

    No Known Activations