© 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. 56934
    Prev
    Next
    INDEX
    Explanations

    pc or gateway

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

    when someone, specifically

    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
    .”
    0.47
    .”[
    0.45
     nosso
    0.44
     optimizing
    0.44
    uestros
    0.44
    .”.
    0.44
     tuan
    0.44
    .`);
    0.43
     solusi
    0.43
    abama
    0.42
    POSITIVE LOGITS
     Textiles
    0.45
    フィルム
    0.44
     Packaging
    0.44
     labelling
    0.43
     প্রথমেই
    0.43
     ஏதாவது
    0.43
    名称
    0.42
     nonprofit
    0.42
     použit
    0.41
     മനു
    0.41
    Activations Density 0.000%

    No Known Activations