© 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. 40968
    Prev
    Next
    INDEX
    Explanations

    brother Bill

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

    reject / module / concepts

    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
    시
    0.50
    いた
    0.48
    Fecha
    0.48
    體
    0.46
    τα
    0.45
    就
    0.45
    고
    0.45
    ताल
    0.44
    체
    0.43
    網
    0.43
    POSITIVE LOGITS
     anthropologists
    0.48
     köy
    0.48
     elektrom
    0.48
     erinner
    0.47
     जादू
    0.47
     anthropological
    0.47
     anthropology
    0.46
     astronauts
    0.46
    roskop
    0.46
    qar
    0.46
    Activations Density 0.000%

    No Known Activations