© 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. 58508
    Prev
    Next
    INDEX
    Explanations

    family traditions

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

    ingredients or measurements

    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
     生地
    0.52
     मकान
    0.50
     ມີ
    0.49
    GLUT
    0.48
     ಯಾವ
    0.48
     ໜອງ
    0.47
     ಆ
    0.46
     ದೊಡ್ಡ
    0.46
     Fabrics
    0.45
     Евро
    0.45
    POSITIVE LOGITS
    ็ก
    0.47
    άρ
    0.46
     atrib
    0.45
    擔任
    0.44
    ەم
    0.44
    дила
    0.43
     cheating
    0.43
    ʻ
    0.43
     ar
    0.42
    ссе
    0.42
    Activations Density 0.000%

    No Known Activations