© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4106
    Prev
    Next
    INDEX
    Explanations

    The neuron flags numeric tokens—especially floating-point numbers (i.e. tokens containing a decimal point).

    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
     the
    0.78
    して
    0.74
     a
    0.71
    ına
    0.68
    ographic
    0.68
     excitation
    0.67
     carcinogenesis
    0.66
     juríd
    0.65
    ของการ
    0.65
     any
    0.65
    POSITIVE LOGITS
    s
    1.20
    snacks
    0.91
    ের
    0.86
    snippets
    0.86
    sø
    0.86
    ों
    0.85
    sning
    0.83
    𝗴
    0.83
    slices
    0.80
    𝘀
    0.79
    Activations Density 0.060%

    No Known Activations