© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25404
    Prev
    Next
    INDEX
    Explanations

    path components or modules

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

    The neuron fires on capitalized module or package names followed by a period (e.g. “Configuration.”, “General.”, “Core.”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isées
    -0.88
     Flüssigkeit
    -0.86
     their
    -0.84
    냉
    -0.79
     niż
    -0.78
     procedure
    -0.77
     awoke
    -0.76
    МЕН
    -0.76
     продукти
    -0.75
     Lordships
    -0.75
    POSITIVE LOGITS
    ᱹ
    0.91
     asmen
    0.89
     jūsų
    0.89
    {}/
    0.88
    ρον
    0.84
     zuerst
    0.84
     dabar
    0.84
    ջ
    0.83
    !");
    0.83
     dieną
    0.82
    Activations Density 0.021%

    No Known Activations