© 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. 41119
    Prev
    Next
    INDEX
    Explanations

    numbers and time spans

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

    demands, needs, sources

    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
     北海道
    0.48
    א
    0.46
    １
    0.45
    photography
    0.44
    攝影
    0.44
    げ
    0.44
    owntown
    0.44
    ３
    0.44
    ８
    0.44
    手機
    0.44
    POSITIVE LOGITS
     lớp
    0.48
     coraz
    0.47
     dès
    0.47
     megsz
    0.46
     начиная
    0.43
     बढ़ता
    0.43
     clase
    0.43
     réforme
    0.42
     semble
    0.42
     mãn
    0.42
    Activations Density 0.000%

    No Known Activations