© 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. 15096
    Prev
    Next
    INDEX
    Explanations

    business and technical terms

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

    code block syntax `()` `{}` `[]` `;` `:`

    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
    或其他
    0.35
     G
    0.34
    或
    0.31
     influence
    0.30
    や
    0.29
    色々
    0.28
    ிகளையும்
    0.28
    G
    0.28
     Vijay
    0.28
     பிரபலமான
    0.28
    POSITIVE LOGITS
     ఇది
    0.45
     இது
    0.42
    这是一个
    0.40
    这是一
    0.39
    입니다
    0.37
     শীর্ষক
    0.37
     는
    0.36
    これは
    0.35
     Ltd
    0.35
    こちらは
    0.35
    Activations Density 0.083%

    No Known Activations