© 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-65K
    7. 30766
    Prev
    Next
    INDEX
    Explanations

    who is or who can

    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_65k_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
     названием
    0.49
    on
    0.46
     ఉపయోగ
    0.46
     プラ
    0.46
     தீங்கு
    0.45
    重量
    0.44
    値
    0.44
    隍
    0.43
    %。
    0.43
     halide
    0.43
    POSITIVE LOGITS
     who
    1.02
    Who
    0.91
    who
    0.88
     Who
    0.84
     quien
    0.79
     siapa
    0.78
    Кто
    0.73
    whom
    0.73
     quienes
    0.69
     whom
    0.68
    Activations Density 0.067%

    No Known Activations