© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    as or than comparisons

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

    The neuron selectively activates on numeric tokens containing decimal points (e.g. “379.0135”, “358.734”, etc.).

    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
     Zeitpunkt
    0.94
    resultlist
    0.91
    Resultado
    0.91
    resultado
    0.88
     Ergebnis
    0.85
    𝗗
    0.84
    Jenis
    0.83
    echolog
    0.82
    𝗪
    0.82
    reportBody
    0.82
    POSITIVE LOGITS
     on
    0.76
    on
    0.75
     allergies
    0.71
     scholarships
    0.71
     vic
    0.70
     globalization
    0.70
     be
    0.69
     labor
    0.68
     diseases
    0.68
    c
    0.68
    Activations Density 0.001%

    No Known Activations