© 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. 7335
    Prev
    Next
    INDEX
    Explanations

    role registered organized October May configured

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

    The neuron identifies large numeric tokens (e.g., four‐digit build or version numbers and other high numerical values).

    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
    Kf
    0.30
    出
    0.30
    một
    0.29
    全面
    0.29
    łaszcza
    0.28
    ر
    0.28
    től
    0.28
    İlk
    0.27
    DataMat
    0.27
    forKey
    0.27
    POSITIVE LOGITS
    .
    0.29
    ’
    0.27
     electrónicos
    0.27
     berwarna
    0.26
     fueron
    0.26
     survived
    0.25
     neighbors
    0.25
     avevano
    0.24
     inmates
    0.24
     miembros
    0.24
    Activations Density 0.000%

    No Known Activations