© 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. 71917
    Prev
    Next
    INDEX
    Explanations

    word followed by of

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

    code, vocab, and specific nouns

    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
     curviliné
    0.54
     كثير
    0.54
     özelliği
    0.52
    撗
    0.51
     маги
    0.49
    툐
    0.49
     abbat
    0.49
    
    0.49
    㞖
    0.48
     itinéraires
    0.48
    POSITIVE LOGITS
    ↵
    0.71
    ↵↵
    0.60
    s
    0.54
    b
    0.50
     Add
    0.49
    <0x0D>
    0.49
     McCulloch
    0.49
     WS
    0.48
     Jul
    0.47
     Ab
    0.45
    Activations Density 0.001%

    No Known Activations