© 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. 98411
    Prev
    Next
    INDEX
    Explanations

    details, specifics,

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

    explanations with details

    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
    桜
    0.51
    DBOutput
    0.48
    cosity
    0.48
    reflectionCamera
    0.48
    ొప్ప
    0.48
    を中心
    0.47
    ཎ
    0.46
    carotene
    0.46
    場の
    0.45
    િક્
    0.45
    POSITIVE LOGITS
     detal
    0.53
     detalhes
    0.53
     подроб
    0.51
     dalam
    0.50
     trong
    0.49
     deta
    0.49
     detalles
    0.48
     ai
    0.48
     opl
    0.48
    >
    0.48
    Activations Density 0.000%

    No Known Activations