© 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. 12387
    Prev
    Next
    INDEX
    Explanations

    amount

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

    The neuron strongly responds to Windows-style filesystem paths (drive letters and backslashes).

    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
     praticamente
    0.88
     فرانس
    0.87
    Spotify
    0.86
     prácticamente
    0.83
    🗸
    0.80
    🧉
    0.80
     চোখের
    0.78
    spotify
    0.78
    COUNTRIES
    0.78
    鼈
    0.78
    POSITIVE LOGITS
     yuan
    0.81
    （
    0.79
     jie
    0.76
    【
    0.74
    baidu
    0.72
    ：
    0.71
    分
    0.71
     zhong
    0.71
    isShow
    0.71
     qq
    0.70
    Activations Density 0.039%

    No Known Activations