© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60743
    Prev
    Next
    INDEX
    Explanations

    driving instructor or father

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

    World, students, return

    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
     source
    0.51
    ри
    0.47
     ファイル
    0.47
     bench
    0.47
    خ
    0.47
     file
    0.46
    لك
    0.46
     cs
    0.46
    Einzel
    0.46
    *;
    0.45
    POSITIVE LOGITS
    த்திற்காக
    0.57
    何时
    0.54
    antikan
    0.52
    েকের
    0.49
     प्रत्ये
    0.49
    hitth
    0.48
    合适的
    0.47
    椁
    0.47
    }}+\
    0.47
     সহিংসতার
    0.46
    Activations Density 0.000%

    No Known Activations