© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12851
    Prev
    Next
    INDEX
    Explanations

    path separator followed by bin or local

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

    This neuron primarily flags absolute filesystem paths (Unix‐style paths starting with “/” and common directories like /usr, /lib, /proc, etc.).

    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
    ▲
    0.64
     জাগ
    0.62
     ▲
    0.59
    वासन
    0.59
    angal
    0.59
     Terbaik
    0.59
     मछ
    0.57
     llrp
    0.57
     Lowell
    0.57
     Flatten
    0.57
    POSITIVE LOGITS
    PYTHON
    0.52
    ੈ
    0.50
     ponies
    0.50
     wir
    0.47
     Profession
    0.47
     vir
    0.47
     Share
    0.47
    share
    0.46
    летнего
    0.46
    python
    0.45
    Activations Density 0.001%

    No Known Activations