© 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. 2417
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on mentions of file‐related terms—especially format names and extensions (e.g. “files,” “formats,” “wav,” “mp3,” “PCM”).

    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
    𝑮
    0.94
    𝑭
    0.93
    явление
    0.93
     Гали
    0.90
    𝑬
    0.88
     valoración
    0.85
     Акаде
    0.82
    Phương
    0.82
     Lakers
    0.80
     quarterfinals
    0.79
    POSITIVE LOGITS
     filesystem
    1.61
     natively
    1.53
     file
    1.41
     Windows
    1.39
     install
    1.36
     installer
    1.36
    インストール
    1.35
     files
    1.34
     firmware
    1.30
     ~/.
    1.27
    Activations Density 0.662%

    No Known Activations