© 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. 146117
    Prev
    Next
    INDEX
    Explanations

    bin features and locations

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

    limerick

    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
     pihak
    0.43
    OLS
    0.42
    ANCEL
    0.40
    主に
    0.39
    חל
    0.39
     মূলত
    0.38
    resposta
    0.38
    ž
    0.38
     ਜਾਂ
    0.38
    ição
    0.38
    POSITIVE LOGITS
     décor
    0.50
     decorate
    0.48
     ব্যাকটেরিয়া
    0.47
     terrific
    0.44
     திருமண
    0.44
     carton
    0.44
     consummate
    0.44
     decorating
    0.43
     রকমের
    0.43
     একাডেমিক
    0.43
    Activations Density 0.000%

    No Known Activations