© 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. 21640
    Prev
    Next
    INDEX
    Explanations

    long, hairy, veins, grooves

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

    biological structures and parts

    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
    上涨
    0.80
    Payroll
    0.79
    美国的
    0.77
    曌
    0.76
    🏦
    0.75
     финансо
    0.74
    钢铁
    0.73
    财政
    0.72
    辈子
    0.72
    大赛
    0.72
    POSITIVE LOGITS
     holotype
    0.85
     G
    0.81
     weakly
    0.79
     forceps
    0.79
     gland
    0.78
     S
    0.78
     ventral
    0.78
     basal
    0.77
     setae
    0.76
     dorsal
    0.75
    Activations Density 0.026%

    No Known Activations