© 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. 116167
    Prev
    Next
    INDEX
    Explanations

    datingsingleswebsitessnacks

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

    **Grain** or description after colon

    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
     backseat
    0.46
    ба
    0.46
    폭
    0.45
    มอ
    0.42
    졍
    0.42
     Sly
    0.41
    เดิม
    0.40
     rápida
    0.40
    永远
    0.40
    Noeud
    0.39
    POSITIVE LOGITS
    insuku
    0.49
     verilen
    0.47
    pumpkin
    0.47
    elling
    0.47
    的情况
    0.46
    再加上
    0.46
    ;
    0.46
     outcrops
    0.45
    score
    0.45
    ur
    0.44
    Activations Density 0.000%

    No Known Activations