© 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. 34743
    Prev
    Next
    INDEX
    Explanations

    C programming: main, printf, stdio

    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
     величе
    0.52
     поко
    0.52
    кова
    0.49
     Це
    0.49
    酺
    0.48
     мав
    0.47
    клю
    0.47
    Celula
    0.46
    蒾
    0.46
    뇰
    0.46
    POSITIVE LOGITS
    bride
    0.48
    bets
    0.45
    gers
    0.44
    berts
    0.43
    oprotein
    0.43
    öz
    0.40
    ATP
    0.40
    ရင်
    0.40
    fts
    0.40
    bing
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.