© 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. 148839
    Prev
    Next
    INDEX
    Explanations

    kill or arrested

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

    reveals, discovers, deleting

    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
    meras
    0.50
    erkraut
    0.49
    iség
    0.48
    ตัวเอง
    0.46
    DBObject
    0.46
    getto
    0.45
     부분이
    0.45
    ❰
    0.45
     휴대
    0.45
     디자인
    0.45
    POSITIVE LOGITS
    らない
    0.46
     sweeping
    0.45
     we
    0.44
     slate
    0.43
    в
    0.42
     coupled
    0.42
    دا
    0.41
    ூர்
    0.40
     complemented
    0.40
    mappings
    0.40
    Activations Density 0.001%

    No Known Activations