© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10189
    Prev
    Next
    INDEX
    Explanations

    institution names and operations

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

    company and organization aspects

    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
     它
    0.53
     দেশটির
    0.52
     திரைப்பட
    0.52
     ପ୍ର
    0.50
     彼
    0.50
     अभ्यर्थियों
    0.49
     ଯ
    0.49
     Thời
    0.49
     പിന്നീട്
    0.49
     Americans
    0.48
    POSITIVE LOGITS
    wide
    0.81
    Wide
    0.54
    ’
    0.51
     mascot
    0.50
     internal
    0.50
    WIDE
    0.49
    internal
    0.48
     wide
    0.48
    '
    0.46
    ロゴ
    0.44
    Activations Density 0.135%

    No Known Activations