© 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. 7032
    Prev
    Next
    INDEX
    Explanations

    story request responses

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

    This neuron activates on numeric tokens, especially floating-point numbers (decimal values).

    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
    end
    0.86
    ok
    0.83
    humidité
    0.81
    elijk
    0.79
    bred
    0.78
    helmet
    0.78
    water
    0.77
     반
    0.77
    ing
    0.75
    ান্ত্রিক
    0.75
    POSITIVE LOGITS
    毫无
    0.75
    个
    0.73
    就需要
    0.73
    衍
    0.71
    فا
    0.68
     futuras
    0.65
     próximas
    0.65
    的老
    0.64
    一部分
    0.64
     distintas
    0.64
    Activations Density 0.001%

    No Known Activations