© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4316
    Prev
    Next
    INDEX
    Explanations

    INT. or EXT. followed by period

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

    The neuron detects tokens that introduce entity metadata or categorical attributes—words like “headquartered,” “based,” “located,” “specializes,” “sells,” or “category” that label details about an organization or item.

    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
    Euro
    0.78
    ələ
    0.72
    larghezza
    0.71
    üle
    0.70
    ärast
    0.69
    莳
    0.68
    Liên
    0.68
    Rice
    0.67
    olian
    0.67
    Jy
    0.67
    POSITIVE LOGITS
     এন্ড
    0.75
     Describes
    0.71
     attains
    0.70
     describes
    0.70
     東京都
    0.70
     cumplen
    0.69
     градусов
    0.68
     verifies
    0.67
     அடைய
    0.66
     एडमिट
    0.66
    Activations Density 0.001%

    No Known Activations