© 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. 80262
    Prev
    Next
    INDEX
    Explanations

    events or specific items

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

    change and impact

    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
    jwt
    0.44
    harga
    0.42
    forgot
    0.42
    従
    0.41
     objekt
    0.40
    hrm
    0.40
     কেনার
    0.40
    ersch
    0.39
    dbcontext
    0.39
    !');
    0.39
    POSITIVE LOGITS
     consecutive
    0.46
     qur
    0.45
     estudia
    0.45
     other
    0.45
     मैथ्स
    0.45
     contiguous
    0.45
     corrects
    0.44
    ęła
    0.44
     Deportivo
    0.44
    ié
    0.43
    Activations Density 0.000%

    No Known Activations