© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14501
    Prev
    Next
    INDEX
    Explanations

    military posture

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

    The neuron is triggered by numerical tokens (especially multi-digit numbers, such as years or counts).

    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
    お客様
    0.76
     ナ
    0.72
    nt
    0.72
     ordination
    0.72
    ntity
    0.71
    the
    0.71
    IMAGES
    0.70
     Austrian
    0.69
    大切
    0.68
     hiv
    0.67
    POSITIVE LOGITS
    aları
    0.86
     đúng
    0.82
    ందే
    0.80
    horns
    0.78
    ढ़े
    0.77
    ousine
    0.77
    ť
    0.77
    classed
    0.77
    grip
    0.77
    żą
    0.75
    Activations Density 0.000%

    No Known Activations