© 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. 199502
    Prev
    Next
    INDEX
    Explanations

    appointed for a termvehicle upto the allocated timeonsite registrationbuyer's ideaaccept

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

    partition function

    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
    diary
    0.53
    delivery
    0.51
    time
    0.46
    lac
    0.45
    '
    0.45
    line
    0.43
    spent
    0.43
    lc
    0.43
    ls
    0.43
     delivery
    0.43
    POSITIVE LOGITS
    Associations
    0.51
    TGFuZ
    0.48
     важ
    0.46
    Desired
    0.46
     язы
    0.46
    <unused696>
    0.46
     zost
    0.45
     samoch
    0.45
    ！」
    0.44
     dramat
    0.44
    Activations Density 0.000%

    No Known Activations