© 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. 186014
    Prev
    Next
    INDEX
    Explanations

    requests, identified, sometimes, taken, scans, pretty

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

    computer concepts and actions

    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
     Birmingham
    0.42
    qm
    0.41
     Wolverhampton
    0.41
     Londra
    0.40
    Edinburgh
    0.39
     Edinburgh
    0.38
    镑
    0.38
    zelfde
    0.38
     Blackpool
    0.38
    ಿಸಿಕೊಳ್ಳ
    0.38
    POSITIVE LOGITS
     তুলনা
    0.45
     😉
    0.44
    😡
    0.43
     তোমার
    0.42
     annoying
    0.42
     lousy
    0.42
     harmless
    0.41
     ০
    0.41
    !',
    0.40
    STRUCTURE
    0.40
    Activations Density 0.000%

    No Known Activations