© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1917
    Prev
    Next
    INDEX
    Explanations

    new intention, on cost

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

    The neuron is triggered by numeric tokens and numeric expressions (digits, numbers, measurements, prices, dosages).

    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_31_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
    J
    0.74
    P
    0.70
    K
    0.70
    Ch
    0.67
    C
    0.64
    M
    0.62
    Y
    0.62
    B
    0.61
    R
    0.61
     J
    0.60
    POSITIVE LOGITS
     perceptive
    0.85
     considerate
    0.79
     conformation
    0.77
     zarówno
    0.75
     commutative
    0.75
     excitatory
    0.74
     drowsiness
    0.74
     borderline
    0.73
     multimeter
    0.73
     antihist
    0.73
    Activations Density 0.494%

    No Known Activations