© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241694
    Prev
    Next
    INDEX
    Explanations

    negative emotions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    <unused44>
    0.76
    ཏ
    0.68
     शादी
    0.67
    sigmaf
    0.67
     Chirurgien
    0.64
     Sebelumnya
    0.63
     ಉತ್ತ
    0.63
    lanelet
    0.62
    leftharpoons
    0.60
    婚
    0.60
    POSITIVE LOGITS
     repudi
    0.74
     tempos
    0.70
     displeasure
    0.68
     rejection
    0.64
    クロス
    0.63
     Cross
    0.58
     rejected
    0.58
     disapproval
    0.58
     investigations
    0.57
     confirmation
    0.56
    Activations Density 0.000%

    No Known Activations