© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    code block continuations

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

    This neuron activates on numeric expressions—especially floating‐point or decimal numbers (often with currency or math notation).

    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
    i
    1.49
    e
    1.16
    ে
    1.02
    a
    0.96
    েও
    0.93
    ीकृत
    0.89
    ه
    0.86
    u
    0.85
    o
    0.84
     मधु
    0.83
    POSITIVE LOGITS
    és
    1.06
    ים
    1.05
    ется
    1.04
    s
    1.04
    ات
    0.96
    ों
    0.95
    ের
    0.93
     publique
    0.93
    的看着
    0.91
    ς
    0.89
    Activations Density 0.001%

    No Known Activations