© 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. 179368
    Prev
    Next
    INDEX
    Explanations

    website addresses

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

    file paths and descriptions

    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
     GridSearchCV
    0.55
     Jie
    0.50
     Miners
    0.50
    <unused46>
    0.50
    gut
    0.49
     Ikat
    0.49
     Minas
    0.49
     Fad
    0.49
     Assoc
    0.48
     Foods
    0.48
    POSITIVE LOGITS
     trasp
    0.47
    톨
    0.46
    ровать
    0.45
    scoring
    0.44
    替え
    0.43
    reliance
    0.43
    следования
    0.43
    多様
    0.43
    торая
    0.42
    し
    0.42
    Activations Density 0.000%

    No Known Activations