© 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. 17097
    Prev
    Next
    INDEX
    Explanations

    understanding

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

    understanding

    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
    Е
    0.92
    ၊
    0.77
    nten
    0.75
     ప
    0.71
    không
    0.71
    binghamton
    0.70
    တွေ
    0.69
    解释
    0.69
    К
    0.69
    Кон
    0.69
    POSITIVE LOGITS
    ר
    1.03
    :
    1.02
    /
    0.97
    ;
    0.91
     (
    0.87
    .
    0.84
     the
    0.84
     D
    0.82
     NO
    0.81
     -
    0.81
    Activations Density 0.035%

    No Known Activations