© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14428
    Prev
    Next
    INDEX
    Explanations

    return from

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

    code punctuation and commands

    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_16k_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
    i
    0.57
    י
    0.50
     g
    0.48
     बाहेर
    0.46
     soh
    0.46
     ));
    0.44
    വശ
    0.44
     sete
    0.43
     compatibility
    0.42
     //.
    0.42
    POSITIVE LOGITS
    NK
    0.50
    TN
    0.50
     Chlorine
    0.49
     Mauer
    0.47
    ٬
    0.47
    MMA
    0.47
    те
    0.46
     Một
    0.46
     وين
    0.46
    ماء
    0.46
    Activations Density 0.002%

    No Known Activations