© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13124
    Prev
    Next
    INDEX
    Explanations

    quirky, unique, unusual

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

    The neuron detects words that signal distinctiveness or novelty—adjectives and terms like “unique,” “unusual,” “odd,” “interesting,” or “stand out.”

    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_31_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
    toHaveBeen
    0.52
    lbrakk
    0.52
    满了
    0.50
     clockRadius
    0.50
    😫
    0.50
    📉
    0.50
     brunes
    0.50
    满满
    0.50
    袷
    0.50
     Brust
    0.49
    POSITIVE LOGITS
    Unique
    2.84
     unique
    2.81
     Unique
    2.77
    unique
    2.73
     uniqueness
    2.70
     unusual
    2.64
     Unusual
    2.63
     уника
    2.59
     UNIQUE
    2.47
     uniques
    2.41
    Activations Density 0.668%

    No Known Activations