© 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. 116541
    Prev
    Next
    INDEX
    Explanations

    Yet, but, in

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

    sarcastic joke

    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
    С
    0.46
     SWT
    0.46
     Recharge
    0.45
    诗
    0.45
    Soy
    0.44
     Cot
    0.44
    راح
    0.44
    ра
    0.43
    Cot
    0.43
    柑
    0.43
    POSITIVE LOGITS
    trimenti
    0.56
    izens
    0.49
     बाद
    0.48
     ยัง
    0.47
    際は
    0.46
    ?’
    0.46
    arming
    0.45
    arded
    0.45
    elipe
    0.45
    udent
    0.44
    Activations Density 0.000%

    No Known Activations