© 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. 9838
    Prev
    Next
    INDEX
    Explanations

    en-

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

    The neuron strongly activates on numeric tokens (e.g. years, version numbers, floating-point literals).

    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
    iverr
    0.63
     racconto
    0.61
    ociazione
    0.60
     رمضان
    0.60
     equação
    0.60
     أ
    0.60
    $...
    0.59
     İslam
    0.59
     වර්ග
    0.59
     rey
    0.58
    POSITIVE LOGITS
    low
    0.48
    ↵↵↵
    0.48
    برها
    0.48
    Similarly
    0.46
    াবদ্ধ
    0.46
     competent
    0.46
    来看
    0.46
     cloak
    0.46
    来
    0.45
     taken
    0.45
    Activations Density 0.006%

    No Known Activations