© 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. 85105
    Prev
    Next
    INDEX
    Explanations

    rights granted or less impairment

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

    Measurement, Bag, collected

    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
     Mumbai
    0.45
    废
    0.43
    ATTRIBUTE
    0.41
     monopolist
    0.41
     Irving
    0.40
    动力
    0.40
     inse
    0.40
    涘
    0.40
     Bombay
    0.40
     এছাড়াও
    0.40
    POSITIVE LOGITS
     gì
    0.50
     året
    0.44
    /
    0.42
    parents
    0.41
    on
    0.41
    as
    0.41
     reservados
    0.40
    VE
    0.40
    res
    0.39
     skoro
    0.39
    Activations Density 0.003%

    No Known Activations