© 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. 1357
    Prev
    Next
    INDEX
    Explanations

    medical advice or treatment

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

    The neuron is detecting Windows‐style file paths (drive letters with backslashes) in log or error messages.

    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
     በጣም
    0.61
     ou
    0.57
    すごい
    0.57
     bah
    0.56
     tome
    0.56
     syl
    0.55
     bud
    0.54
     sandalwood
    0.54
    dessä
    0.53
     robbers
    0.52
    POSITIVE LOGITS
    mf
    0.62
    esterol
    0.58
    KG
    0.56
    getParent
    0.55
    ｉ
    0.54
    Ray
    0.54
    parent
    0.52
    Ec
    0.52
     দিল
    0.52
    Parent
    0.52
    Activations Density 0.055%

    No Known Activations