© 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. 77933
    Prev
    Next
    INDEX
    Explanations

    governance and repair actions

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

    liar/discharge/ports/deletes/balances/plants/efficient/using

    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
     বাদ
    0.52
     밑
    0.46
    刚
    0.46
     ஆரம்பித்த
    0.45
     আরম্ভ
    0.44
    之后的
    0.43
    注意
    0.43
     সম্বন্ধ
    0.43
     сорти
    0.43
    밑
    0.43
    POSITIVE LOGITS
     lyr
    0.56
    otu
    0.52
    allelujah
    0.46
    IC
    0.46
    olus
    0.46
     ول
    0.44
     نړۍ
    0.44
     लो
    0.42
    OLO
    0.42
    lcd
    0.42
    Activations Density 0.001%

    No Known Activations