© 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. 11275
    Prev
    Next
    INDEX
    Explanations

    documenting or licensing

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

    This neuron detects terms and tokens related to software release and distribution (e.g. “release,” “binary,” “distribution,” version numbers, tags, 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
     MyApplication
    0.63
     optimizer
    0.63
     scheduler
    0.61
     appartement
    0.59
     samsung
    0.59
     숨
    0.57
     ottim
    0.57
    ❊
    0.57
     Optimization
    0.56
    숨
    0.56
    POSITIVE LOGITS
    License
    0.65
    banners
    0.63
     licensee
    0.61
     banner
    0.59
     License
    0.58
     banners
    0.57
    license
    0.56
    arange
    0.56
     license
    0.56
     licence
    0.55
    Activations Density 0.035%

    No Known Activations