© 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. 3561
    Prev
    Next
    INDEX
    Explanations

    difficulty levels: low, medium, hard

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

    The neuron fires on standalone numeric tokens (especially those with decimal points) that represent quantitative values such as prices, durations, identifiers, or limits.

    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
    :
    0.58
     correspondences
    0.55
     correspondents
    0.54
     corresponding
    0.52
     temperatures
    0.51
     correspondent
    0.50
     hypotheses
    0.50
    :_
    0.50
     references
    0.49
    对应的
    0.49
    POSITIVE LOGITS
     거의
    0.67
     ¿?
    0.65
     %)
    0.62
     खूप
    0.60
     yksi
    0.59
     вероятно
    0.58
     इत्यादी
    0.55
    %)
    0.55
     엄청
    0.55
     फक्त
    0.54
    Activations Density 0.008%

    No Known Activations