© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15388
    Prev
    Next
    INDEX
    Explanations

    number of years

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

    This neuron activates on numeric tokens representing decimal numbers (floats).

    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
     foods
    0.76
     foodstuffs
    0.72
    嶼
    0.72
    ّم
    0.70
    воря
    0.67
    ല്ലാം
    0.67
    ंमुळे
    0.66
    itriangular
    0.63
    arser
    0.63
     عج
    0.63
    POSITIVE LOGITS
     Luciano
    0.88
    맥
    0.87
    ｩ
    0.85
    owneri
    0.84
    怆
    0.84
    ルー
    0.83
    ໃນ
    0.82
     Aura
    0.81
    日で
    0.80
     Genn
    0.80
    Activations Density 0.000%

    No Known Activations