© 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. 252272
    Prev
    Next
    INDEX
    Explanations

    server or build infrastructure

    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
    拙
    0.43
     Monmouth
    0.41
    渤
    0.41
    平成
    0.39
    imwrite
    0.39
    淯
    0.38
     viện
    0.38
    تف
    0.38
    গ্রন্থ
    0.38
     خیال
    0.38
    POSITIVE LOGITS
     shelves
    0.47
    δα
    0.46
     RP
    0.45
    ៧
    0.45
    да
    0.44
     specially
    0.43
     lum
    0.43
     classifications
    0.42
    కం
    0.42
     cpu
    0.42
    Activations Density 0.000%

    No Known Activations