© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81627
    Prev
    Next
    INDEX
    Explanations

    your body and pleasure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wei
    0.45
     charging
    0.44
    我在
    0.44
    πη
    0.44
    aff
    0.44
    ↵↵
    0.44
    et
    0.43
    ox
    0.43
    p
    0.42
    wick
    0.41
    POSITIVE LOGITS
     ದ
    0.48
     {}>,
    0.46
     pillar
    0.45
    Specifically
    0.45
    ális
    0.45
     للس
    0.44
     Президента
    0.44
     দফা
    0.43
     부
    0.43
     పెద్ద
    0.43
    Activations Density 0.002%

    No Known Activations