© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 141408
    Prev
    Next
    INDEX
    Explanations

    hurriedly released

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

    stolen yen, Wagner Group

    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
    Negative Logits
    T
    0.48
    Waar
    0.46
    circle
    0.46
    Volunteer
    0.45
    Tool
    0.45
    N
    0.45
    Ten
    0.44
    DIM
    0.44
    SER
    0.44
    Circle
    0.43
    POSITIVE LOGITS
    បន្ថែម
    0.52
     Raptors
    0.52
     fu
    0.51
     Glu
    0.50
     Remains
    0.50
     ε
    0.49
     dá
    0.49
     minions
    0.49
     Roofing
    0.48
     ə
    0.48
    Activations Density 0.000%

    No Known Activations