© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185853
    Prev
    Next
    INDEX
    Explanations

    crisis, drugs, or revoked

    np_acts-logits-general · gemini-2.5-flash-lite

    action after specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    u
    0.69
    l
    0.58
    o
    0.57
    oy
    0.55
    a
    0.54
    direction
    0.54
    tie
    0.52
    uencia
    0.52
    vao
    0.50
    e
    0.50
    POSITIVE LOGITS
     delegated
    0.54
     revoke
    0.50
     PPT
    0.48
     revoked
    0.47
     LGA
    0.46
     Crisp
    0.45
     SOAP
    0.45
     syringe
    0.44
     Drugs
    0.44
     bombarded
    0.44
    Activations Density 0.002%

    No Known Activations