© 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. 46918
    Prev
    Next
    INDEX
    Explanations

    several years or downstream concepts

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

    modest, grand, intricate

    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
     dumpfile
    0.48
    حياته
    0.44
    Vocabulary
    0.41
    旯
    0.41
    人で
    0.40
    を獲得
    0.40
    惰
    0.40
    ﹙
    0.40
    ?-
    0.39
     অভিভাব
    0.39
    POSITIVE LOGITS
     Nawaz
    0.47
     QSOs
    0.46
     Nawab
    0.46
     MeOH
    0.45
     lö
    0.44
     ricord
    0.43
     Sabine
    0.43
     Lloyds
    0.43
    ificação
    0.43
     Ã
    0.43
    Activations Density 0.000%

    No Known Activations