© 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. 8070
    Prev
    Next
    INDEX
    Explanations

    current events and explanations

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

    The neuron strongly activates on numeric tokens (e.g. integers and decimal numbers).

    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
    et
    0.82
    ద
    0.75
    a
    0.73
    k
    0.71
    kc
    0.71
    רים
    0.70
    iak
    0.69
    किला
    0.68
    ยังมี
    0.67
     অস্ত
    0.66
    POSITIVE LOGITS
    。.
    0.78
    。</
    0.78
     botón
    0.77
     página
    0.77
     paréntesis
    0.75
     desviación
    0.75
    。。
    0.75
     शूट
    0.75
     possibilité
    0.75
    ></
    0.74
    Activations Density 0.001%

    No Known Activations