© 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. 74928
    Prev
    Next
    INDEX
    Explanations

    may contact

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

    controlling AC power

    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
     ポリエステル
    0.48
     μορ
    0.48
     dô
    0.47
    ggio
    0.46
     asympt
    0.46
     সাম
    0.46
    🦞
    0.46
     শক
    0.46
    rodní
    0.46
     fisc
    0.45
    POSITIVE LOGITS
     clumsy
    0.50
    чи
    0.48
    Iranian
    0.48
    ک
    0.47
    inguish
    0.46
    обы
    0.45
    B
    0.45
    InputNum
    0.45
    the
    0.44
     Committee
    0.44
    Activations Density 0.001%

    No Known Activations