© 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. 242708
    Prev
    Next
    INDEX
    Explanations

    the boot sequence

    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
    baseball
    0.54
    ಾನೂ
    0.49
    場面
    0.46
    機会
    0.46
     বাহিনী
    0.44
    醾
    0.44
    provide
    0.43
     बेसब
    0.43
    沐
    0.43
    渚
    0.43
    POSITIVE LOGITS
     contrasts
    0.58
    ata
    0.57
     beggar
    0.53
     asymmetric
    0.49
     gord
    0.49
     dignified
    0.48
    ينه
    0.47
     hindering
    0.47
     asymmetrical
    0.46
    ıyla
    0.46
    Activations Density 0.000%

    No Known Activations