© 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. 76323
    Prev
    Next
    INDEX
    Explanations

    recommendations from site

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

    detailed descriptions or specific ratings

    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
    ｴ
    0.54
    可愛い
    0.53
    は
    0.51
    ಾರ್
    0.49
    Έ
    0.49
     kerana
    0.48
    参考
    0.48
    阿
    0.48
     colleague
    0.47
    💚
    0.47
    POSITIVE LOGITS
     Arizona
    0.44
     jurisdictions
    0.44
     diverses
    0.43
     automakers
    0.43
     firms
    0.42
     fighters
    0.42
     أخرى
    0.42
     jednotliv
    0.41
     tiers
    0.41
     Databases
    0.41
    Activations Density 0.006%

    No Known Activations