© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10352
    Prev
    Next
    INDEX
    Explanations

    respectively

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

    The neuron is triggered by numeric tokens, especially decimal or floating-point numbers in the text.

    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
     Fight
    0.85
    ’
    0.72
    യുള്ള
    0.71
    捋
    0.70
    </strong>
    0.70
     morales
    0.69
    сня
    0.68
     brave
    0.66
    лык
    0.66
    Coref
    0.66
    POSITIVE LOGITS
    秶
    0.86
    ᆢ
    0.81
     amelyet
    0.77
    ט
    0.76
     એન
    0.75
    ್ಟ
    0.74
     ਸਕ
    0.73
     amely
    0.73
     Dünya
    0.70
     ()=>
    0.70
    Activations Density 0.001%

    No Known Activations