© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

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

    The neuron strongly activates on multi-digit numeric tokens (e.g. parts of phone numbers, codes, prices), i.e. it detects numeric sequences.

    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
    ":[],
    0.61
    க்கெ
    0.60
     భాగంగా
    0.54
    ствии
    0.54
     ১২শ
    0.52
     tiempos
    0.52
    ราว
    0.52
     বসবাস
    0.52
    คนิค
    0.52
     সাহায্যে
    0.52
    POSITIVE LOGITS
    ′
    1.04
    ″
    1.04
    ′,
    0.73
    /-
    0.70
     sayılı
    0.66
    /+
    0.66
    ½
    0.64
    円
    0.63
    mAh
    0.62
    ⁩
    0.62
    Activations Density 0.496%

    No Known Activations