© 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. 8757
    Prev
    Next
    INDEX
    Explanations

    along with, Option, PlusOne

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

    The neuron strongly fires on specific named entities or specialized technical terms (e.g. proper nouns and domain-specific vocabulary).

    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
    C
    0.71
    J
    0.69
    K
    0.66
    B
    0.66
    А
    0.66
    W
    0.65
    A
    0.64
    V
    0.63
    F
    0.63
    С
    0.63
    POSITIVE LOGITS
     Zoro
    0.64
     antioxidants
    0.62
     Zoho
    0.62
     chemot
    0.62
     outras
    0.61
     shrubs
    0.61
     germanium
    0.61
     accessoires
    0.59
     vías
    0.59
     autres
    0.59
    Activations Density 3.514%

    No Known Activations