© 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. 13167
    Prev
    Next
    INDEX
    Explanations

    Explanation of neuron 4 behavior: the main thing this neuron does is find floating‐point numeric literals (tokens representing numbers with 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
    Bibliographie
    0.88
    لومات
    0.81
     inapplicable
    0.79
    ни
    0.77
    Commun
    0.76
    矚
    0.76
    espèce
    0.75
    NOVEMBER
    0.75
     visitation
    0.74
    创始人
    0.74
    POSITIVE LOGITS
    -
    0.86
    )
    0.78
    ),
    0.76
    ,
    0.74
    .
    0.72
    ?
    0.70
    z
    0.68
    ck
    0.67
    揍
    0.66
    irin
    0.66
    Activations Density 0.285%

    No Known Activations