© 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. 23148
    Prev
    Next
    INDEX
    Explanations

    closing quotes followed by connectors

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

    punctuation and appositive clauses

    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
    س
    0.96
    s
    0.66
    ج
    0.66
    m
    0.64
    ר
    0.62
    g
    0.61
    𝟬
    0.61
    ن
    0.60
    ס
    0.60
    手
    0.59
    POSITIVE LOGITS
    
    0.65
    ,
    0.60
    ',
    0.59
    *
    0.56
    ologii
    0.55
    ;
    0.55
    ządz
    0.54
     includ
    0.53
    igis
    0.52
    até
    0.52
    Activations Density 0.063%

    No Known Activations