© 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. 124067
    Prev
    Next
    INDEX
    Explanations

    common word sequences

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

    legal system, data accounts

    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
    ת
    0.54
    auh
    0.47
    adress
    0.46
    as
    0.46
    ay
    0.45
    andrew
    0.45
    dong
    0.44
    t
    0.43
    苡
    0.43
    ouna
    0.42
    POSITIVE LOGITS
     നാല
    0.52
    ണിത്
    0.47
    షణ
    0.47
    жидан
    0.46
    屻
    0.45
    شة
    0.44
     deleteTask
    0.44
     Szen
    0.43
     buna
    0.43
     htmlFor
    0.42
    Activations Density 0.000%

    No Known Activations