© 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. 3661
    Prev
    Next
    INDEX
    Explanations

    shell commands or code snippets

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

    This neuron detects numeric expressions that report a team’s changing lead or score (e.g., “cut the lead to 5–3,” “took the lead to 26,” “cut the gap to 6–5”).

    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
    s
    0.85
    ous
    0.80
    nae
    0.80
     سلام
    0.72
     new
    0.71
     anc
    0.71
     Anspr
    0.69
     society
    0.68
     famille
    0.68
     ese
    0.67
    POSITIVE LOGITS
    ра
    0.98
    ר
    0.93
    MAY
    0.88
    лично
    0.85
    ลด
    0.85
    侮
    0.82
    䬲
    0.82
    YOU
    0.82
    줬
    0.81
    榞
    0.80
    Activations Density 0.008%

    No Known Activations