© 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. 203642
    Prev
    Next
    INDEX
    Explanations

    motorcycle cc denominations

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

    health, risk, and identity

    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
    ooo
    0.47
    感知
    0.47
     oldu
    0.46
    怂
    0.45
     œufs
    0.45
     deuda
    0.44
    微博
    0.44
    要知道
    0.43
    না
    0.43
     _|
    0.43
    POSITIVE LOGITS
     भरपूर
    0.51
     buttermilk
    0.48
     কক্ষে
    0.48
    raut
    0.47
     commuter
    0.47
     widgets
    0.47
     cheeky
    0.47
    ontinuous
    0.46
    Thirty
    0.46
    collegiate
    0.46
    Activations Density 0.000%

    No Known Activations