© 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. 131901
    Prev
    Next
    INDEX
    Explanations

    vaccine from, two such, be sufficient

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

    features snack strategy literature ownership

    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
    i
    0.69
    to
    0.63
    ي
    0.52
    glia
    0.51
    raq
    0.51
    ra
    0.49
    e
    0.49
    いろんな
    0.48
    a
    0.48
    lingu
    0.47
    POSITIVE LOGITS
     staked
    0.46
     COUNTY
    0.44
     DIFFICULTY
    0.43
     メーカー
    0.42
     giocatori
    0.41
     stubbornly
    0.41
     チェ
    0.41
     occuper
    0.41
     スト
    0.40
     carport
    0.40
    Activations Density 0.000%

    No Known Activations