© 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. 124852
    Prev
    Next
    INDEX
    Explanations

    direct free kick

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

    IRA, APR, cru

    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
    itag
    0.49
     Grâce
    0.47
     चाह
    0.46
     autonom
    0.46
     marts
    0.46
     Crunchy
    0.45
    ⦕
    0.44
     ateliers
    0.43
     wakt
    0.43
    kast
    0.43
    POSITIVE LOGITS
     Ric
    0.47
     horizontal
    0.47
    5
    0.46
    DEM
    0.46
    0.46
    ↵↵
    0.45
    USU
    0.45
     sanguin
    0.44
     consistently
    0.43
    Elect
    0.43
    Activations Density 0.000%

    No Known Activations