© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9006
    Prev
    Next
    INDEX
    Explanations

    numerical list indicators

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

    The neuron responds specifically to floating-point numbers (i.e. numeric 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_31_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
     ninety
    0.54
     Melting
    0.52
    摡
    0.51
     thirty
    0.50
     melting
    0.49
     θεω
    0.49
     relativamente
    0.48
    บค้น
    0.48
     αυ
    0.47
     forty
    0.46
    POSITIVE LOGITS
    1
    1.49
    <0x91>
    1.22
    １
    1.01
    ১
    0.95
    ١
    0.91
    १
    0.89
    ۱
    0.86
    ૧
    0.86
    
    0.85
    ១
    0.80
    Activations Density 0.069%

    No Known Activations