© 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. 146316
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    justifying topics and listing categorizations

    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
     cultured
    0.52
     khớp
    0.46
    রে
    0.46
     popularly
    0.45
    Ꮔ
    0.44
     transcript
    0.43
     horizontally
    0.43
     parâ
    0.43
    rach
    0.43
     moim
    0.42
    POSITIVE LOGITS
    小売
    0.47
    মনসিংহ
    0.44
     最新
    0.42
     Anzahl
    0.42
    団体
    0.42
    <unused1039>
    0.40
    āl
    0.40
     Announced
    0.40
     追加
    0.40
    à
    0.39
    Activations Density 0.001%

    No Known Activations