© 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. 11438
    Prev
    Next
    INDEX
    Explanations

    hang or hanging

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

    The neuron fires on occurrences of the word “hang” (and its inflected forms like “hung” or “hanging”).

    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
    蛊
    0.61
    diagnostic
    0.60
    ريط
    0.57
    Diag
    0.57
     contenuti
    0.55
    plotly
    0.55
     Diagnostic
    0.53
    ینہ
    0.52
     diagnostic
    0.52
     Erwach
    0.52
    POSITIVE LOGITS
     hang
    1.79
     hangs
    1.75
     hanging
    1.73
    挂
    1.65
     hung
    1.63
     Hanging
    1.59
    Hang
    1.58
    hang
    1.55
    hanging
    1.55
     Hang
    1.54
    Activations Density 0.156%

    No Known Activations