© 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. 160802
    Prev
    Next
    INDEX
    Explanations

    enumerated, system, judge, lamps, surface

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

    technical terms and symbols

    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
    abilă
    0.63
     peony
    0.54
    Dummy
    0.48
    룰
    0.48
     kemenangan
    0.47
     vivienda
    0.47
     если
    0.46
     মৃত্যু
    0.46
     одно
    0.46
     রোগের
    0.46
    POSITIVE LOGITS
     McIntyre
    0.48
    $\\
    0.46
     percorso
    0.45
     Chorus
    0.45
    臺
    0.45
     Brent
    0.44
    0.44
    \\\
    0.43
     McCullough
    0.42
     Spartans
    0.42
    Activations Density 0.000%

    No Known Activations