© 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. 217676
    Prev
    Next
    INDEX
    Explanations

    any / if / upon / to condition or expectation

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

    sleep deprivation accelerates

    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
     Field
    0.47
    9
    0.46
    getString
    0.46
    辅
    0.44
     本
    0.41
    ﻪ
    0.41
    ﻔ
    0.41
    通
    0.40
     nors
    0.40
    f
    0.40
    POSITIVE LOGITS
    트는
    0.54
    트를
    0.51
    مجھے
    0.51
    🌔
    0.50
    を開催
    0.49
    🎱
    0.48
    OID
    0.48
    🌓
    0.48
    অন্যদিকে
    0.48
    ત
    0.46
    Activations Density 0.000%

    No Known Activations