© 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. 144232
    Prev
    Next
    INDEX
    Explanations

    astrology, sun signs

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

    multilingual conversation responses

    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
    ม่
    0.49
    chronic
    0.48
    farming
    0.47
    termination
    0.45
     تلاش
    0.45
    rukh
    0.45
    ν
    0.45
     خوا
    0.44
    cathode
    0.44
    ин
    0.44
    POSITIVE LOGITS
     总
    0.46
     noche
    0.46
     deportivo
    0.45
     evaluator
    0.45
     cuarta
    0.45
     obscured
    0.43
     返回
    0.43
     カスタ
    0.43
     daytime
    0.42
     MESSAGE
    0.42
    Activations Density 0.000%

    No Known Activations