© 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. 247073
    Prev
    Next
    INDEX
    Explanations

    published books "HR"

    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
     Wasn
    0.54
    aço
    0.53
     KOM
    0.51
    CCI
    0.50
     katanya
    0.50
    쾺
    0.49
     jezika
    0.49
     aantal
    0.48
    袒
    0.48
    られています
    0.48
    POSITIVE LOGITS
    ur
    0.55
    ert
    0.52
    eight
    0.50
    our
    0.48
    通过
    0.47
     Эд
    0.46
    shall
    0.45
    urches
    0.45
    kms
    0.45
    ures
    0.44
    Activations Density 0.000%

    No Known Activations