© 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. 6631
    Prev
    Next
    INDEX
    Explanations

    lists of numbers or lists of words

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

    This neuron detects floating-point numbers (numerical tokens containing a decimal point).

    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
    ی
    0.91
     entfer
    0.85
    næ
    0.82
    ե
    0.82
    יים
    0.81
    e
    0.79
    aus
    0.79
    dur
    0.77
     시간에
    0.76
    a
    0.76
    POSITIVE LOGITS
     locomotive
    0.80
     Brésil
    0.80
     குறிப்பாக
    0.76
    を持って
    0.74
     protruding
    0.73
     cumbersome
    0.70
     criticised
    0.69
     kneeling
    0.69
     rifle
    0.69
    쿄
    0.69
    Activations Density 0.002%

    No Known Activations