© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1619
    Prev
    Next
    INDEX
    Explanations

    Python imports

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

    This neuron responds to floating-point numbers (numeric tokens containing a decimal point).

    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
    kách
    0.54
    Jwt
    0.52
    Issuer
    0.48
    亨
    0.48
    եց
    0.46
    ducers
    0.46
    가
    0.46
    에서
    0.46
    HANDLER
    0.45
     ครับ
    0.45
    POSITIVE LOGITS
     centimeter
    0.60
     color
    0.54
     random
    0.53
     time
    0.52
    時間
    0.52
    时间和
    0.52
     calcium
    0.50
     sinistra
    0.50
     bandeja
    0.49
     temperatura
    0.48
    Activations Density 0.004%

    No Known Activations