© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203675
    Prev
    Next
    INDEX
    Explanations

    Databricks jobs and SQL

    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
    Assignments
    0.49
    Report
    0.47
    Publication
    0.47
    T
    0.46
    User
    0.45
    oft
    0.44
    Pulse
    0.44
    Hop
    0.43
    Wash
    0.43
     Report
    0.43
    POSITIVE LOGITS
    ル
    0.46
     கவு
    0.45
     overruling
    0.45
     environ
    0.45
     promot
    0.45
     Croatia
    0.44
     Croatian
    0.44
    看到
    0.44
     Dragonfly
    0.44
     zebrafish
    0.43
    Activations Density 0.003%

    No Known Activations