© 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. 3412
    Prev
    Next
    INDEX
    Explanations

    numbers after punctuation

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

    The neuron detects negative numeric tokens (i.e. a minus sign directly preceding a 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
    k
    0.71
     וא
    0.68
    ্যালি
    0.64
    迋
    0.62
    ﺢ
    0.61
    ỡng
    0.59
    se
    0.56
     nový
    0.56
     alfalfa
    0.55
     כן
    0.55
    POSITIVE LOGITS
    communic
    0.77
    conoc
    0.73
     //-
    0.67
    NERVE
    0.67
    ्रोल
    0.64
     ومع
    0.63
     মিলিয়ন
    0.63
    риб
    0.63
     bedeut
    0.62
     обраща
    0.62
    Activations Density 0.007%

    No Known Activations