© 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. 85385
    Prev
    Next
    INDEX
    Explanations

    online identifiers and specific names

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

    alphanumeric identifiers

    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
    Negative Logits
     atacar
    0.37
    opar
    0.36
    pson
    0.36
    rish
    0.36
    {}{
    0.36
    気になる
    0.35
    Popup
    0.35
    bsch
    0.35
    intellij
    0.35
    opp
    0.35
    POSITIVE LOGITS
    ቢያ
    0.44
     owning
    0.44
     Dioxide
    0.38
     specification
    0.38
     euros
    0.37
     Benedict
    0.37
     categorization
    0.36
    वारीत
    0.36
     bytes
    0.36
    拥
    0.36
    Activations Density 0.000%

    No Known Activations