© 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. 67195
    Prev
    Next
    INDEX
    Explanations

    analog electronics and devices

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

    analog computers, clocks, and input

    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
    in
    0.70
    to
    0.64
    tin
    0.57
    tia
    0.54
    the
    0.54
    ncia
    0.54
    h
    0.53
    t
    0.52
    ti
    0.51
     SEARCH
    0.51
    POSITIVE LOGITS
    رة
    0.58
    약을
    0.52
     altas
    0.52
    약
    0.51
    妤
    0.48
    接近
    0.48
    时间
    0.47
    ه‌
    0.47
    事情
    0.47
     analgesic
    0.47
    Activations Density 0.070%

    No Known Activations