© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    key responsibilities

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

    This neuron detects words that introduce enumerations or lists (e.g., “several,” “four,” “two,” “main,” “number”).

    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
     Quad
    0.69
    rodite
    0.69
     turun
    0.68
     思っ
    0.68
     あの
    0.66
     赵
    0.66
     ጡ
    0.64
    것도
    0.64
    rawberry
    0.64
     まで
    0.64
    POSITIVE LOGITS
     factors
    1.23
    因素
    1.12
    factors
    1.09
     factores
    1.00
     characteristics
    1.00
     факторов
    0.97
     факторы
    0.95
    Factors
    0.94
    characteristics
    0.92
     reasons
    0.89
    Activations Density 0.217%

    No Known Activations