© 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. 90075
    Prev
    Next
    INDEX
    Explanations

    Party gained, gain, airing, Judah said

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

    running applications on spark

    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
     HIV
    0.51
     Ebola
    0.51
     Viruses
    0.48
     []:
    0.47
     Crisis
    0.47
     AIDS
    0.46
     Auschwitz
    0.46
     LSTM
    0.46
     Dokl
    0.45
     Quot
    0.45
    POSITIVE LOGITS
    愉
    0.50
    PlayerData
    0.48
    ूम
    0.47
    犬
    0.45
    έν
    0.44
    ግብ
    0.44
    Deer
    0.43
    jogador
    0.43
    笑顔
    0.43
     hráč
    0.42
    Activations Density 0.003%

    No Known Activations