© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92571
    Prev
    Next
    INDEX
    Explanations

    function return types

    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
    <0x91>
    0.47
    зон
    0.46
    𒀊
    0.46
    મેટ
    0.44
     Zugriff
    0.43
    리스
    0.43
    nameSort
    0.43
    MVCProject
    0.43
    UseDebug
    0.41
     variously
    0.41
    POSITIVE LOGITS
     comfort
    0.47
    v
    0.46
     d
    0.43
    a
    0.40
    g
    0.40
    f
    0.40
     अय्यर
    0.40
    ㄡ
    0.39
     good
    0.39
     fish
    0.39
    Activations Density 0.013%

    No Known Activations