© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13552
    Prev
    Next
    INDEX
    Explanations

    states of being or quality

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

    This neuron fires on emotionally charged, qualitative words—abstract nouns and adjectives that convey depth, passion, or intensity.

    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
    trends
    0.80
     wallets
    0.80
     casinos
    0.79
    scoreboard
    0.76
    headers
    0.74
     hassles
    0.73
     collectibles
    0.73
    experts
    0.72
    services
    0.72
     warten
    0.71
    POSITIVE LOGITS
     ludicrous
    0.98
     poetry
    0.95
    껏
    0.90
     lyrical
    0.88
     reinterpret
    0.88
     precludes
    0.88
     absurdity
    0.88
    ateness
    0.87
     Phenomenology
    0.87
     poesia
    0.87
    Activations Density 2.314%

    No Known Activations