© 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. 35785
    Prev
    Next
    INDEX
    Explanations

    Player of the Year

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

    but, or, and

    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
     любых
    0.46
    ലോക
    0.45
    閇
    0.45
    мец
    0.43
    児
    0.43
    }}}{\
    0.43
    мень
    0.43
    ведений
    0.42
    equival
    0.42
    善
    0.42
    POSITIVE LOGITS
     chipset
    0.52
     Sherwood
    0.49
    rawberry
    0.48
     serine
    0.48
     serotonin
    0.46
    artet
    0.46
     بالت
    0.46
     Tomato
    0.45
     ionization
    0.44
     Galleria
    0.44
    Activations Density 0.000%

    No Known Activations