© 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. 62125
    Prev
    Next
    INDEX
    Explanations

    lists, courses, or classifications

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

    oversaw significant infrastructure

    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
     द्रविड़
    0.50
     сла
    0.48
    м
    0.47
     МО
    0.45
     рей
    0.45
     рее
    0.44
    ብ
    0.44
    в
    0.44
     даст
    0.43
     Май
    0.43
    POSITIVE LOGITS
    ilibrium
    0.48
    valence
    0.46
     subgraph
    0.45
     buckling
    0.45
     Bihar
    0.44
    accom
    0.43
     kpc
    0.43
     बिहार
    0.42
    INATION
    0.42
    缓解
    0.42
    Activations Density 0.000%

    No Known Activations