© 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. 177439
    Prev
    Next
    INDEX
    Explanations

    corporation and company information

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

    website, code, list, names, numbers

    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
     matériau
    0.50
    逡
    0.49
    ্বার
    0.47
    т
    0.47
    ேஷ்
    0.47
     nutrientes
    0.46
    bec
    0.46
     materiais
    0.45
    клю
    0.45
    囯
    0.45
    POSITIVE LOGITS
    vdots
    0.45
     Jésus
    0.45
     निगम
    0.43
     corporation
    0.43
     hormone
    0.42
     veterinary
    0.42
    又能
    0.42
    }>\
    0.42
    تاجها
    0.41
     संगठन
    0.41
    Activations Density 0.000%

    No Known Activations