© 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. 116158
    Prev
    Next
    INDEX
    Explanations

    phrases with words indicating possession or description

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

    simplex, sympathetic nervous, resource, elements, direction, skills

    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
     YOLO
    0.54
    ियाँ
    0.46
    ﻚ
    0.46
     T
    0.46
    থন
    0.45
     ব্যবস্থা
    0.44
     MEGA
    0.44
    ﺶ
    0.43
    conditioning
    0.43
    申し上げ
    0.43
    POSITIVE LOGITS
    )}^
    0.46
     own
    0.43
    ாதார
    0.43
     mq
    0.43
    Mq
    0.42
    KURZBESCHREIBUNG
    0.42
    扛
    0.41
    朼
    0.41
    ovatel
    0.41
    ною
    0.41
    Activations Density 0.000%

    No Known Activations