© 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. 9644
    Prev
    Next
    INDEX
    Explanations

    skilled, pains, login, fit

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

    This neuron strongly activates on numeric tokens (especially multi-digit numbers and decimals), such as reference numbers or statistics 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
    a
    0.93
    j
    0.89
    v
    0.87
    },$
    0.82
    jc
    0.78
    jr
    0.76
    இது
    0.75
    i
    0.73
    Uploading
    0.72
    в
    0.72
    POSITIVE LOGITS
    紅色
    0.82
     Parkinson
    0.80
     dese
    0.76
     Державний
    0.76
     siger
    0.75
     branca
    0.73
     Debido
    0.73
     देखकर
    0.73
     Wyd
    0.72
    OnError
    0.72
    Activations Density 0.000%

    No Known Activations