© 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. 96130
    Prev
    Next
    INDEX
    Explanations

    electronic equipment

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

    multiple languages and informal speech

    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
    -
    0.72
    ing
    0.53
     truncated
    0.49
     inclinations
    0.48
     editions
    0.47
    woods
    0.46
     tether
    0.46
     ferns
    0.46
    z
    0.46
    b
    0.46
    POSITIVE LOGITS
    Đi
    0.49
    各位同學
    0.48
     Hlav
    0.47
    দে
    0.47
    ruž
    0.45
    一丝
    0.45
    呥
    0.45
    appliquer
    0.44
    Hlav
    0.44
     Kontrolle
    0.44
    Activations Density 0.000%

    No Known Activations