© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7776
    Prev
    Next
    INDEX
    Explanations

    layout, hanging fruit, digging, electric, cash

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

    The neuron is primarily triggered by concrete, often compound, nouns referring to physical equipment or specialized tools.

    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
     زنان
    0.63
    !='
    0.61
     تھے
    0.60
     rů
    0.60
     cottura
    0.60
     bibliothèque
    0.58
    ঽ
    0.57
    anwhile
    0.56
    "":
    0.56
    もあった
    0.56
    POSITIVE LOGITS
    ﻭ
    0.84
    ደጋ
    0.72
     casinos
    0.71
    が存在
    0.71
    த்தூர்
    0.70
     casino
    0.70
     जोकि
    0.70
    entiti
    0.68
     bettors
    0.66
     그리고
    0.66
    Activations Density 1.002%

    No Known Activations