© 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. 153378
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    people and roles

    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
     communément
    0.43
    typescript
    0.42
     encom
    0.41
     percolation
    0.41
    🎣
    0.40
     psor
    0.39
     microcos
    0.39
    _.
    0.38
     selections
    0.38
    माजिक
    0.38
    POSITIVE LOGITS
     अस्थायी
    0.41
    த்தான்
    0.40
    ató
    0.39
    Gain
    0.38
    and
    0.38
    French
    0.38
    İ
    0.38
    丢失
    0.38
    ੂ
    0.38
     Ingram
    0.37
    Activations Density 0.001%

    No Known Activations