© 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. 125221
    Prev
    Next
    INDEX
    Explanations

    still have, lots of, corner of

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

    song chorus

    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
     хвати
    0.49
     শক্তির
    0.49
    鱔
    0.49
     وګ
    0.47
     enthalpies
    0.47
    ьера
    0.47
     верно
    0.46
     ജൂ
    0.46
     ሽፋ
    0.45
     увеличения
    0.45
    POSITIVE LOGITS
    DS
    0.49
     s
    0.47
     Goldman
    0.47
     Deaf
    0.47
     as
    0.46
     stay
    0.46
     Hospital
    0.46
    金
    0.45
     relative
    0.45
     game
    0.44
    Activations Density 0.000%

    No Known Activations