© 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. 128092
    Prev
    Next
    INDEX
    Explanations

    artist, language, necessary, you

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

    User and Product descriptions

    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
    ದುಕೊಳ್ಳ
    0.55
     আন্দোল
    0.54
    ’।
    0.50
     보험
    0.50
    距离
    0.49
    出会
    0.49
    ᑎ
    0.49
    rv
    0.48
    長さ
    0.48
     거리
    0.47
    POSITIVE LOGITS
     Sempre
    0.47
     này
    0.45
     Zebra
    0.44
     Boeh
    0.44
     Match
    0.43
     Loma
    0.43
     G
    0.43
     Vor
    0.42
     Wett
    0.42
     .
    0.42
    Activations Density 0.000%

    No Known Activations