© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 488
    Prev
    Next
    INDEX
    Explanations

    you to get

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

    punctuation and code constructs

    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
    ↵↵
    0.39
    .'
    0.36
    ma
    0.34
     .'
    0.33
    ↵↵↵
    0.32
    ↵↵↵↵↵↵↵↵
    0.32
    ten
    0.32
    .’
    0.32
    xpress
    0.31
    ↵↵↵↵↵↵↵↵↵
    0.31
    POSITIVE LOGITS
     thậm
    0.39
    вый
    0.37
     будь
    0.37
    さは
    0.35
    लेषण
    0.34
     сне
    0.34
    ствием
    0.34
    ногие
    0.34
    と思いますが
    0.34
    σιμοποι
    0.34
    Activations Density 0.003%

    No Known Activations