© 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. 166551
    Prev
    Next
    INDEX
    Explanations

    broken glass

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

    PoC, commands, instead of, absorbed

    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
    Przyp
    0.54
    梸
    0.52
    ”）
    0.51
     dní
    0.49
    цый
    0.49
    Operational
    0.49
    瘫
    0.49
    艐
    0.48
    utzt
    0.48
    两年
    0.48
    POSITIVE LOGITS
    起了
    0.53
     National
    0.53
     governmental
    0.52
     Catherine
    0.51
     magnitude
    0.51
     was
    0.49
     solar
    0.49
     believers
    0.48
     small
    0.48
     Lithuanian
    0.48
    Activations Density 0.000%

    No Known Activations