© 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. 15409
    Prev
    Next
    INDEX
    Explanations

    convert units

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

    The main thing this neuron does is detect numeric values—especially decimal or measurement figures—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
    odzi
    0.84
     그걸
    0.83
     myös
    0.82
    लिब्र
    0.81
     오히려
    0.81
    ल्पन
    0.79
    <unused2009>
    0.78
     تلك
    0.77
    zięk
    0.76
    ޟ
    0.76
    POSITIVE LOGITS
    ;
    1.03
     or
    0.96
    ?
    0.90
    หรือ
    0.89
     или
    0.88
     (
    0.87
     atau
    0.83
    -
    0.82
     but
    0.82
    /
    0.82
    Activations Density 0.002%

    No Known Activations