© 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. 12429
    Prev
    Next
    INDEX
    Explanations

    python code in pandas

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

    The neuron activates on numeric tokens with decimal points, i.e. floating-point 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
     умолчанию
    0.84
    toluene
    0.77
    ference
    0.73
     ય
    0.73
    t
    0.72
    tion
    0.72
    sing
    0.71
    nats
    0.71
     runoff
    0.70
     Ð
    0.70
    POSITIVE LOGITS
    何度も
    0.76
    なんと
    0.75
    これからも
    0.75
    àn
    0.73
    되고
    0.70
    なお
    0.70
    एफ
    0.69
     availed
    0.68
    二人
    0.68
    계를
    0.68
    Activations Density 0.000%

    No Known Activations