© 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. 112590
    Prev
    Next
    INDEX
    Explanations

    Talmud

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

    write a rap song

    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
    히
    0.58
    மர்
    0.49
     appartiennent
    0.48
    ங்கள்
    0.48
     lequel
    0.48
     chromatographic
    0.48
     CASCADE
    0.47
    ব
    0.47
    там
    0.47
     MODIFY
    0.47
    POSITIVE LOGITS
     Cal
    0.54
     Sacramento
    0.49
     Accuracy
    0.49
     Mc
    0.48
     Bench
    0.48
     Price
    0.47
     Bits
    0.46
    cal
    0.45
     Sak
    0.45
     Ad
    0.45
    Activations Density 0.001%

    No Known Activations