© 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. 9298
    Prev
    Next
    INDEX
    Explanations

    individually hand

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

    in small batches, individually

    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
    InterfaceLine
    0.56
     活动
    0.55
     ζωή
    0.53
    狲
    0.49
    禟
    0.49
    𒅴
    0.49
    𒉈
    0.48
     গলায়
    0.47
     sAlarm
    0.47
     spolupr
    0.47
    POSITIVE LOGITS
     U
    0.62
     I
    0.57
     B
    0.57
     and
    0.55
    ED
    0.54
     D
    0.54
    orders
    0.53
    <b>
    0.53
     as
    0.53
     MB
    0.52
    Activations Density 0.000%

    No Known Activations