© 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. 13089
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized in picking up floating‐point numbers (tokens representing decimal numeric 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
    !
    0.56
     satin
    0.55
     sequins
    0.54
    !);
    0.51
     herewith
    0.50
     apricots
    0.49
     sarcasm
    0.48
     seagulls
    0.48
     defec
    0.47
     panties
    0.47
    POSITIVE LOGITS
     माइक
    0.47
     memoir
    0.46
     이름
    0.46
    眽
    0.44
    채
    0.43
    囊
    0.43
    erdere
    0.42
    endu
    0.42
    ନ୍ଦ
    0.42
    频
    0.41
    Activations Density 0.000%

    No Known Activations