© 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. 2040
    Prev
    Next
    INDEX
    Explanations

    output commands

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

    The neuron activates on numeric tokens—especially floating-point numbers—wherever they appear in the text.

    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
     invierno
    0.55
     Juillet
    0.52
     Europas
    0.51
     révolution
    0.49
     ¡
    0.48
     juillet
    0.46
     nourr
    0.46
     sobrevivir
    0.46
     yǐ
    0.46
    édé
    0.46
    POSITIVE LOGITS
    頴
    0.52
    <unused342>
    0.46
    <unused2148>
    0.46
    нням
    0.45
    сэн
    0.44
    ла
    0.43
    Current
    0.42
    Edition
    0.42
    <unused347>
    0.42
    όμε
    0.42
    Activations Density 0.001%

    No Known Activations