© 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. 100782
    Prev
    Next
    INDEX
    Explanations

    action verbs and concepts

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

    breaking down concepts

    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
    КА
    0.49
    гія
    0.47
    도
    0.46
    निवेश
    0.45
    에
    0.45
     praia
    0.44
    ло
    0.44
    ба
    0.44
    ҳа
    0.44
    ور
    0.43
    POSITIVE LOGITS
     Kentucky
    0.49
     PTSD
    0.49
    getConfig
    0.49
     SWAT
    0.49
    0.49
    )=\
    0.47
     Chevy
    0.47
     চালানো
    0.47
     NASCAR
    0.46
     CEOs
    0.46
    Activations Density 0.003%

    No Known Activations