© 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. 13503
    Prev
    Next
    INDEX
    Explanations

    Index block or header

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

    The neuron selectively activates on decimal-formatted numeric tokens (floating-point 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
    ">
    0.55
     GSR
    0.53
    ?/
    0.53
    /">
    0.53
     gehad
    0.52
     Knoll
    0.52
    \!
    0.52
    שורים
    0.51
     Prony
    0.50
     ॥
    0.50
    POSITIVE LOGITS
     яка
    0.64
    aigne
    0.63
    reflectionMap
    0.61
    当你
    0.61
    ның
    0.59
    ಡುವುದ
    0.59
    ৰ
    0.59
    Respondent
    0.59
     вашего
    0.58
    дать
    0.57
    Activations Density 0.588%

    No Known Activations