© 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. 117711
    Prev
    Next
    INDEX
    Explanations

    estate planning, mining, hematology, dumpster

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

    geriatric, familiar, contractors, copied, already, sales

    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
    for
    0.55
    ado
    0.55
    from
    0.50
     werd
    0.49
    sch
    0.49
    atil
    0.49
    at
    0.48
    k
    0.47
    arest
    0.47
    as
    0.47
    POSITIVE LOGITS
    롬
    0.50
    yfikacji
    0.50
     홈
    0.49
     Jharkhand
    0.48
     गोप
    0.48
     인한
    0.47
    ൃത
    0.47
     MQ
    0.46
     {{-
    0.46
     платы
    0.45
    Activations Density 0.000%

    No Known Activations