© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric or alphanumeric sequences (e.g. multi‐digit numbers, coordinates, zip codes, or mixed digit/letter tokens).

    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
    as
    0.67
    at
    0.66
    al
    0.60
    r
    0.59
    y
    0.56
    in
    0.55
    ar
    0.55
    2
    0.55
    os
    0.54
    an
    0.54
    POSITIVE LOGITS
    infodisc
    0.42
    वून
    0.41
    <unused15>
    0.41
     aussch
    0.40
    <unused51>
    0.39
    ismillahirrah
    0.39
    <unused32>
    0.39
    jähr
    0.38
    <unused75>
    0.38
     mó
    0.37
    Activations Density 1.496%

    No Known Activations