© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15541
    Prev
    Next
    INDEX
    Explanations

    Chef Secretary

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

    The neuron is primarily detecting numeric tokens (i.e. explicit numbers or number‐like strings).

    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
     ouverte
    0.75
    蘊
    0.73
     angust
    0.72
    facing
    0.72
    e
    0.71
    
    0.71
     coûts
    0.70
    quera
    0.70
     roto
    0.69
    y
    0.68
    POSITIVE LOGITS
    ię
    0.83
    な
    0.82
     usual
    0.80
    ाइड
    0.77
    ہ
    0.77
    ości
    0.76
    ior
    0.75
    รา
    0.75
    なっている
    0.75
    的情况下
    0.73
    Activations Density 0.000%

    No Known Activations