© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 198576
    Prev
    Next
    INDEX
    Explanations

    posted in by

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

    Memory, random, MSRP, feminist

    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
    數
    0.61
    నులు
    0.59
    璫
    0.57
    醜
    0.55
    ٱ
    0.55
    珵
    0.54
    న్లు
    0.52
    増
    0.51
    栻
    0.50
    錒
    0.50
    POSITIVE LOGITS
    penet
    0.47
    reading
    0.46
    inae
    0.46
    ículos
    0.46
     khổ
    0.46
    kuensi
    0.46
    illar
    0.45
     thập
    0.44
    くない
    0.44
    </em>
    0.44
    Activations Density 0.000%

    No Known Activations