© 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. 228813
    Prev
    Next
    INDEX
    Explanations

    unique items and locations

    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
     abnormally
    0.48
    ings
    0.45
    est
    0.44
    G
    0.44
    enn
    0.44
    Reilly
    0.44
     Schroeder
    0.43
    po
    0.42
    et
    0.42
     unusually
    0.42
    POSITIVE LOGITS
     vudd
    0.56
    🦵
    0.55
    🐫
    0.54
     menengah
    0.53
     zmdi
    0.53
     halfCanvas
    0.52
     儿童
    0.51
     生活
    0.50
     sedangkan
    0.50
     consape
    0.50
    Activations Density 0.000%

    No Known Activations