© 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. 1605
    Prev
    Next
    INDEX
    Explanations

    orthographic / transliterated terms

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

    spiritual and human 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
     แถม
    0.36
     NYPD
    0.32
     दिलचस्प
    0.32
     দারুণ
    0.31
     πίνακα
    0.30
    έ
    0.30
     snag
    0.29
    शियल
    0.29
     dettaglio
    0.29
    մ
    0.29
    POSITIVE LOGITS
     انسان
    0.35
     രോഗ
    0.32
     orthodox
    0.30
     fundamento
    0.29
     interdependent
    0.28
     अनेक
    0.28
     anthropogenic
    0.28
     conson
    0.28
     insanın
    0.28
     neoplastic
    0.28
    Activations Density 0.000%

    No Known Activations