© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2882
    Prev
    Next
    INDEX
    Explanations

    thoughts about harmful urges

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

    This neuron activates on mentions of dreams or dreaming (e.g., “dream,” “dreamed,” “vivid dream,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_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
    ‌ی
    0.75
     SLO
    0.71
    я
    0.70
    %>%
    0.69
     aesthetics
    0.67
    не
    0.64
    ‌ای
    0.64
    ль
    0.63
     RF
    0.63
     GPIO
    0.63
    POSITIVE LOGITS
     dreamt
    0.79
    放題
    0.78
    胰
    0.76
    浻
    0.75
    으로
    0.74
     segura
    0.72
     imaginations
    0.71
    шымта
    0.70
     sonhos
    0.70
     surm
    0.70
    Activations Density 0.003%

    No Known Activations