© 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. 144461
    Prev
    Next
    INDEX
    Explanations

    business and foreign labels

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

    discussing risks and fulfillment

    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
    𝐳
    0.57
    örk
    0.52
    inks
    0.50
     төр
    0.50
    rived
    0.49
     melod
    0.49
     किया
    0.48
    raiz
    0.47
    ട്ടി
    0.47
     चेयर
    0.47
    POSITIVE LOGITS
     پوش
    0.45
    制造商
    0.44
    ح
    0.44
    گذ
    0.43
    海军
    0.43
    ول
    0.42
     Firms
    0.42
    ペ
    0.42
    Quand
    0.42
    بغ
    0.42
    Activations Density 0.000%

    No Known Activations