© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4214
    Prev
    Next
    INDEX
    Explanations

    economic, social, emotional, delivery, sheen, schema

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

    The neuron is primarily detecting numeric tokens (i.e. 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
    رر
    0.58
    cccc
    0.56
    триму
    0.55
    0
    0.54
     Чи
    0.54
    小
    0.53
     三
    0.53
    मध्यप्रदेश
    0.52
    л
    0.52
    三
    0.52
    POSITIVE LOGITS
     exigences
    0.68
     dynamism
    0.67
     artistry
    0.65
     structure
    0.64
     mechanisms
    0.63
     infrastructure
    0.61
     processes
    0.61
     husbandry
    0.60
     organizacional
    0.60
    法规
    0.60
    Activations Density 0.268%

    No Known Activations