© 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. 9155
    Prev
    Next
    INDEX
    Explanations

    explanation, covering

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

    This neuron specializes in detecting numeric tokens—especially multi‐digit numbers with decimal points.

    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
     The
    0.50
    2
    0.50
     J
    0.48
     T
    0.47
     www
    0.46
     twenty
    0.46
    the
    0.45
     Robert
    0.44
     Jeffrey
    0.44
     the
    0.44
    POSITIVE LOGITS
     אבל
    0.63
    <h2>
    0.56
    <strong>
    0.53
    <h3>
    0.52
     nhưng
    0.51
    نید
    0.49
     👇
    0.47
     కానీ
    0.47
     biasa
    0.46
     있지만
    0.46
    Activations Density 0.842%

    No Known Activations