© 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. 247735
    Prev
    Next
    INDEX
    Explanations

    Lamar Colorado the Union Regist safe Bedroom candidates

    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
    ষ্কৃত
    0.47
    cY
    0.46
    ວດ
    0.45
     час
    0.45
    dSample
    0.44
     exploded
    0.44
    护
    0.44
    Hour
    0.44
     çöze
    0.44
     hour
    0.43
    POSITIVE LOGITS
     Polygon
    0.45
     Botanic
    0.43
     Diplomacy
    0.43
     Mature
    0.42
    auche
    0.42
     Infirm
    0.42
    uf
    0.41
     Caledonia
    0.41
    摒
    0.41
     Carn
    0.40
    Activations Density 0.000%

    No Known Activations