© 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. 9194
    Prev
    Next
    INDEX
    Explanations

    voter ID number

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

    live commerce

    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
     bytes
    0.40
     algéb
    0.38
     résult
    0.36
     opcode
    0.36
     ejes
    0.36
     objectives
    0.36
     समझने
    0.36
     />}
    0.36
     aider
    0.35
     analyser
    0.35
    POSITIVE LOGITS
    jakarta
    0.46
    🇵
    0.46
     대한민국
    0.45
     Jakarta
    0.43
    🇹
    0.43
     한국
    0.41
    한국
    0.41
     столи
    0.41
    🇮
    0.41
    城市
    0.40
    Activations Density 0.194%

    No Known Activations