© 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. 194870
    Prev
    Next
    INDEX
    Explanations

    names and specific contexts

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

    creating presentations

    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
    ir
    0.49
    erp
    0.45
    z
    0.45
    wei
    0.45
     shenanigans
    0.45
     ups
    0.44
    code
    0.43
    vist
    0.42
     zarar
    0.42
    y
    0.42
    POSITIVE LOGITS
     waarvan
    0.54
     wohn
    0.49
     cuya
    0.48
     শিক্ষক
    0.48
    даго
    0.48
    يدات
    0.48
     ganzen
    0.47
     amelyet
    0.47
    韪
    0.47
     CASES
    0.46
    Activations Density 0.001%

    No Known Activations