© 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. 4860
    Prev
    Next
    INDEX
    Explanations

    A LOT, a photo

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

    offer APIs

    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
     adaptarse
    0.46
     Mixed
    0.44
    快
    0.42
    亚
    0.41
     Adam
    0.41
     Forward
    0.41
     Perimeter
    0.41
    ป
    0.40
     Quentin
    0.40
     Electron
    0.39
    POSITIVE LOGITS
     ಏಕೆ
    0.57
    agamanam
    0.57
    death
    0.56
    agl
    0.54
    roly
    0.53
    entity
    0.53
    lty
    0.53
     parenteral
    0.52
     ে
    0.52
    cdt
    0.51
    Activations Density 0.000%

    No Known Activations