© 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. 132425
    Prev
    Next
    INDEX
    Explanations

    average if back box returned

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

    tables, uniforms, temples, loneliness

    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
    Season
    0.53
    UN
    0.48
    ብሰ
    0.47
    US
    0.46
    acci
    0.46
    ;
    0.45
    Play
    0.44
    U
    0.42
    シーズン
    0.42
    UB
    0.41
    POSITIVE LOGITS
     triste
    0.51
     digo
    0.51
     eficaz
    0.49
     โอ้
    0.47
    洼
    0.47
     করিতাম
    0.47
     nCmdShow
    0.46
     никогда
    0.46
    !!!");
    0.46
     treinamento
    0.46
    Activations Density 0.000%

    No Known Activations