© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11499
    Prev
    Next
    INDEX
    Explanations

    good workingenemy linesprevent too manywell-rounded personalong lineage

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

    This neuron activates on the “b.” token that marks birth‐date entries (the “b.” prefix before a date).

    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
    éfonos
    0.83
    K
    0.82
    A
    0.79
    C
    0.76
    Pur
    0.75
    Al
    0.72
     sklearn
    0.72
     เจ
    0.71
    F
    0.71
    J
    0.71
    POSITIVE LOGITS
     remedied
    1.01
    рата
    0.95
    𝒕
    0.89
     whom
    0.86
     corrected
    0.85
    ونی
    0.82
     theirs
    0.82
    瞍
    0.81
    ет
    0.80
     corrective
    0.80
    Activations Density 0.001%

    No Known Activations