© 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. 3156
    Prev
    Next
    INDEX
    Explanations

    End of

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

    This neuron responds to decorative or emphatic non-alphanumeric symbols (e.g. emojis, arrows, currency icons) used in the text.

    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
     Clemens
    0.65
    ര
    0.64
     Peirce
    0.63
    ọ
    0.58
     McClure
    0.57
     adequada
    0.57
     gesam
    0.56
     Pearce
    0.56
     Dekker
    0.55
     kohta
    0.55
    POSITIVE LOGITS
     ใส่
    0.77
    ።
    0.75
    РА
    0.70
    ។
    0.70
    ><
    0.70
     бере
    0.68
     式
    0.68
     Hãy
    0.68
     arrhythmias
    0.66
    fony
    0.66
    Activations Density 0.011%

    No Known Activations