© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8876
    Prev
    Next
    INDEX
    Explanations

    RPG settings

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

    This neuron fires most strongly on numeric quantities—especially decimal numbers and other measurement values.

    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
     cedo
    0.83
     tervez
    0.83
     उदा
    0.79
    ži
    0.77
     повышение
    0.76
     годы
    0.76
     tomada
    0.76
    ﻋ
    0.75
     Deshalb
    0.74
     novembro
    0.73
    POSITIVE LOGITS
     워
    0.93
    ো
    0.86
    ど
    0.84
     attuned
    0.76
    ्स
    0.74
    л
    0.73
    ાં
    0.73
    ੁੰ
    0.73
    ં
    0.72
     puffs
    0.72
    Activations Density 0.000%

    No Known Activations