© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7965
    Prev
    Next
    INDEX
    Explanations

    variable naming conventions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    echolog
    0.29
     Sereth
    0.29
    !।
    0.28
     आरोग
    0.28
    辏
    0.28
    vaegir
    0.27
     dalších
    0.27
    positroid
    0.27
    GTUIKit
    0.27
    溽
    0.27
    POSITIVE LOGITS
     with
    0.34
     at
    0.33
     request
    0.31
    ↵
    0.28
     sectors
    0.28
     string
    0.28
     a
    0.28
     d
    0.27
     v
    0.27
     these
    0.27
    Activations Density 0.273%

    No Known Activations