© 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. 151520
    Prev
    Next
    INDEX
    Explanations

    asset region

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

    current flowing, file named

    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
    䳕
    0.57
    ቒ
    0.57
    Ꮸ
    0.53
    ඪ
    0.53
    뷊
    0.53
    ጶ
    0.53
    গ্ত
    0.52
    停车场
    0.52
    ीडियो
    0.52
    მასრულ
    0.50
    POSITIVE LOGITS
    ;
    0.63
    us
    0.61
    3
    0.61
    ur
    0.61
    ,
    0.60
    ap
    0.59
    <0x0D>
    0.57
    9
    0.57
    </h2>
    0.56
    f
    0.55
    Activations Density 0.000%

    No Known Activations