© 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. 204531
    Prev
    Next
    INDEX
    Explanations

    related with

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

    suggested visual

    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
    0.55
    顯示
    0.45
     sai
    0.44
     aussi
    0.44
    ↵↵
    0.43
     vivid
    0.43
     gior
    0.41
    \
    0.41
    សា
    0.41
     red
    0.40
    POSITIVE LOGITS
    ików
    0.50
    CONCEPT
    0.47
    Bsky
    0.46
    撂
    0.46
    ovjek
    0.45
     নিজেদের
    0.44
    Sever
    0.44
    getSaveLocation
    0.44
    aanse
    0.44
     गुला
    0.43
    Activations Density 0.003%

    No Known Activations