© 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. 249077
    Prev
    Next
    INDEX
    Explanations

    part of or used by

    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
     основные
    0.47
    larghezza
    0.46
    <unused414>
    0.45
     વિવિધ
    0.44
    ası
    0.44
    多様
    0.44
     длина
    0.43
     అన్ని
    0.43
    เฉพาะ
    0.43
     다양한
    0.43
    POSITIVE LOGITS
     azonban
    0.44
     například
    0.43
     a
    0.43
     internals
    0.43
     mellitus
    0.41
     sarebbero
    0.40
     iemand
    0.39
     resembling
    0.39
     yd
    0.39
     sewage
    0.39
    Activations Density 0.002%

    No Known Activations