© 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. 9567
    Prev
    Next
    INDEX
    Explanations

    impuissant

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

    This neuron fires on media-file format tokens (e.g. “MP3,” “MP4,” 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
    plement
    0.68
     apt
    0.66
    කින්
    0.64
    ்த்து
    0.63
    пла
    0.62
    Missing
    0.61
    闖
    0.60
    <unused22>
    0.58
    PSON
    0.57
    釁
    0.57
    POSITIVE LOGITS
    ion
    0.72
    ylobacter
    0.71
    agna
    0.70
    aired
    0.66
    grounds
    0.66
    éu
    0.66
    ereur
    0.64
    ionat
    0.64
    ere
    0.63
    ocalypse
    0.63
    Activations Density 0.355%

    No Known Activations