© 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. 4427
    Prev
    Next
    INDEX
    Explanations

    attribute, limits, url, page

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

    Rounding values

    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
     крово
    0.18
     бактери
    0.18
    <unused75>
    0.18
    痢
    0.18
     увла
    0.18
    窰
    0.17
     اربع
    0.17
     فونب
    0.17
    rifugal
    0.17
    廡
    0.17
    POSITIVE LOGITS
    _
    0.26
     data
    0.22
    Data
    0.22
    -
    0.22
    Node
    0.21
    IDs
    0.20
    ers
    0.20
     IDs
    0.19
    Value
    0.19
    To
    0.19
    Activations Density 0.013%

    No Known Activations