© 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. 14478
    Prev
    Next
    INDEX
    Explanations

    ends or is

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

    The neuron is keyed to tokens representing numeric data or measurements (numbers, often multi-digit or decimal).

    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
    Analysis
    0.65
    at
    0.62
    fig
    0.62
    analysis
    0.61
     I
    0.60
    k
    0.59
    T
    0.59
    EB
    0.57
    SHE
    0.55
    Crop
    0.55
    POSITIVE LOGITS
     receives
    0.77
    自身の
    0.71
     యొక్క
    0.69
     retains
    0.68
     exposes
    0.66
    自体
    0.64
     secures
    0.64
     enforces
    0.64
     himself
    0.64
     maintains
    0.63
    Activations Density 0.002%

    No Known Activations