© 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. 9597
    Prev
    Next
    INDEX
    Explanations

    GERD, VM, Synthetic

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

    The neuron fires on numeric tokens—especially floating‐point or decimal numbers.

    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
    谥
    0.93
    Antoine
    0.86
     retomar
    0.82
     étale
    0.81
     moieties
    0.77
    ተት
    0.77
    frontier
    0.76
     बत्रा
    0.76
    栈
    0.76
    翘
    0.76
    POSITIVE LOGITS
    n
    0.87
    ng
    0.83
     يجب
    0.82
     site
    0.81
    1
    0.80
     Debit
    0.79
    ort
    0.79
     take
    0.77
     Delete
    0.76
    lle
    0.75
    Activations Density 0.000%

    No Known Activations