© 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. 9067
    Prev
    Next
    INDEX
    Explanations

    appreciation for your contributions

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

    The neuron strongly activates on numeric tokens (especially floating‐point or citation‐style 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
     caminho
    0.86
     astfel
    0.84
     beş
    0.83
     allí
    0.82
    5
    0.80
     cinq
    0.78
     tüm
    0.78
     fazendo
    0.78
    char
    0.78
     alemão
    0.77
    POSITIVE LOGITS
    ских
    0.84
     incineration
    0.80
    াহ্ম
    0.79
    ນ
    0.79
    Ἄ
    0.77
     advancements
    0.73
     concentrations
    0.72
    ALA
    0.72
    Послед
    0.71
     thermocou
    0.71
    Activations Density 0.000%

    No Known Activations