© 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. 11268
    Prev
    Next
    INDEX
    Explanations

    programming code explanations

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

    The neuron fires on lines where the writer describes a problem or asks for help—i.e. user-issue statements or questions.

    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
     (-\
    0.62
     (*
    0.58
     illustrating
    0.58
     intuit
    0.58
     হোমিওপ্যাথ
    0.57
     ggplot
    0.57
     TensorFlow
    0.57
     approximations
    0.56
     automorphisms
    0.55
     intuitive
    0.55
    POSITIVE LOGITS
    ）.
    0.60
    ꒱
    0.59
    )....
    0.57
    .…
    0.55
    ）,
    0.55
    シール
    0.55
    )...
    0.55
    )…
    0.54
    NewLabel
    0.54
     Dorn
    0.53
    Activations Density 0.006%

    No Known Activations