© 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. 139900
    Prev
    Next
    INDEX
    Explanations

    individuals meeting

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

    first cooperation performance

    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
    ্যাম
    0.46
     замени
    0.45
    substituted
    0.44
    elser
    0.42
    bufs
    0.41
     கழு
    0.41
     אחד
    0.41
     ی
    0.40
    дони
    0.40
    ceq
    0.40
    POSITIVE LOGITS
     माझा
    0.49
    ২
    0.48
    展開
    0.47
    ত
    0.47
    團
    0.47
     Jahrhunderts
    0.46
     испол
    0.45
     Visconti
    0.45
     তাক
    0.45
    ledovatel
    0.44
    Activations Density 0.000%

    No Known Activations