© 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. 217120
    Prev
    Next
    INDEX
    Explanations

    observation and emotion

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

    conditions and states

    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
    0.53
    jam
    0.52
     ağı
    0.47
    ają
    0.46
     problème
    0.46
     máme
    0.46
     송
    0.45
    wast
    0.45
    awiają
    0.45
     pruž
    0.45
    POSITIVE LOGITS
     CALIFORNIA
    0.57
     ILLINOIS
    0.48
     INTERNATIONAL
    0.46
    出血
    0.46
    บริเวณ
    0.44
    $\--
    0.43
     JUN
    0.43
     OCTOBER
    0.43
    鍍
    0.43
     নিহত
    0.42
    Activations Density 0.001%

    No Known Activations