© 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. 22638
    Prev
    Next
    INDEX
    Explanations

    scoring play

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

    levels, increase, domains, improvement

    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
    锶
    0.46
    Tourist
    0.46
    Terrain
    0.45
    Cups
    0.44
    ARTS
    0.43
     निर्ण
    0.42
     rougeâtres
    0.42
     품질
    0.42
    Sunflower
    0.42
     differs
    0.42
    POSITIVE LOGITS
     మంత్రి
    0.47
     فِي
    0.45
    ゼン
    0.43
    ឆ្នាំ
    0.43
    瞥
    0.43
     অস্বাভাবিক
    0.42
    新年
    0.41
    値下げ
    0.40
    猜
    0.40
    ချင်း
    0.40
    Activations Density 0.000%

    No Known Activations