© 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. 170360
    Prev
    Next
    INDEX
    Explanations

    friend or foe

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

    ignore, exclude, irrelevant

    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
    ensure
    0.61
    ij
    0.48
    ong
    0.46
    owl
    0.46
    рованного
    0.46
    I
    0.46
    IP
    0.45
     ensure
    0.45
    enge
    0.45
    distributed
    0.45
    POSITIVE LOGITS
     живо
    0.52
    案件
    0.47
     batal
    0.47
     గేమ్
    0.46
    蚋
    0.45
     usaha
    0.44
    牲
    0.44
     但是
    0.44
     టా
    0.44
     ль
    0.44
    Activations Density 0.001%

    No Known Activations