© 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. 74175
    Prev
    Next
    INDEX
    Explanations

    Janeiro, Coco

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

    wit sharper than any rebuke

    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
    溂
    0.47
    濵
    0.47
     fender
    0.44
     aquilo
    0.44
     BOOKS
    0.43
    ਾਨੂੰ
    0.43
     assassination
    0.42
     ethnographic
    0.42
    闿
    0.42
     Ethnicity
    0.41
    POSITIVE LOGITS
     añadido
    0.54
    žil
    0.50
     dedicato
    0.49
     Marzo
    0.47
    পুরুষ
    0.46
    abbanti
    0.46
    hoch
    0.45
    ()}
    0.44
    Dn
    0.44
    PVC
    0.44
    Activations Density 0.000%

    No Known Activations