© 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. 47453
    Prev
    Next
    INDEX
    Explanations

    Authentic or radical statements

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

    names, places, styles

    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
    exponent
    0.48
    結論
    0.47
    揖
    0.46
     asymptotic
    0.45
     are
    0.45
    lable
    0.44
    abline
    0.44
    fou
    0.44
    criterion
    0.43
     japon
    0.42
    POSITIVE LOGITS
     服
    0.46
     ಸಾಮಾನ್ಯ
    0.46
     আর্মি
    0.45
     הר
    0.44
    IMENTAL
    0.44
     શિક્ષ
    0.43
     বসব
    0.43
    썩
    0.43
     участ
    0.42
     Monuments
    0.42
    Activations Density 0.000%

    No Known Activations