© 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. 19058
    Prev
    Next
    INDEX
    Explanations

    news articles and releases

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

    news articles and headlines

    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
    ↵
    1.06
     It
    1.05
    <0x0D>
    1.01
    It
    0.97
    In
    0.95
     If
    0.91
     In
    0.90
    If
    0.90
    </code>
    0.88
    0.88
    POSITIVE LOGITS
    사
    1.41
    드
    1.02
    ア
    0.97
    ない
    0.94
    ಕ್
    0.94
    ме
    0.92
    א
    0.91
    ای
    0.91
    업
    0.89
    К
    0.89
    Activations Density 0.020%

    No Known Activations