© 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. 152702
    Prev
    Next
    INDEX
    Explanations

    features and offers accommodation

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

    briefed colleague

    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
    é
    0.48
    fé
    0.45
    arid
    0.45
     Anwendungen
    0.43
     approbation
    0.43
    😛
    0.43
    },-
    0.43
    ato
    0.42
    {
    0.42
     innoc
    0.42
    POSITIVE LOGITS
     WERE
    0.45
    ชัน
    0.44
     चरित्र
    0.44
     sponsor
    0.42
     보시면
    0.42
     হয়েছিলেন
    0.42
     cơn
    0.42
     리그
    0.41
    라면
    0.41
     প্রসার
    0.41
    Activations Density 0.000%

    No Known Activations