© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139205
    Prev
    Next
    INDEX
    Explanations

    metals, card, experiment, short

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

    controlled demolition

    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
    lasts
    0.52
    Louisiana
    0.46
    lic
    0.45
    button
    0.45
    league
    0.45
    likelihood
    0.45
    p
    0.45
    post
    0.45
    time
    0.44
    ча
    0.44
    POSITIVE LOGITS
     میرے
    0.57
     друзей
    0.53
    ✊
    0.49
     אני
    0.49
    vänd
    0.49
    itriangular
    0.48
     माझी
    0.48
     اسرائیل
    0.47
     моих
    0.47
     dédié
    0.47
    Activations Density 0.000%

    No Known Activations