© 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. 11541
    Prev
    Next
    INDEX
    Explanations

    force multiplied by time

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

    The neuron is specifically triggered by the token “1,” i.e. it detects standalone occurrences of the digit 1.

    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
    いき
    0.64
     steps
    0.63
    भ
    0.61
    ो
    0.59
    有哪些
    0.58
    二
    0.58
     worse
    0.57
    ています
    0.57
     ladder
    0.57
    榔
    0.56
    POSITIVE LOGITS
     gerais
    1.02
     DeFi
    0.95
     TFA
    0.94
    ச்சா
    0.93
     PFAS
    0.91
     AISI
    0.90
     eSIM
    0.89
     Deloitte
    0.89
     PKD
    0.89
    čar
    0.89
    Activations Density 0.013%

    No Known Activations