© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67141
    Prev
    Next
    INDEX
    Explanations

    type and category

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

    The neuron responds to technical or specialized terms—especially class labels, model numbers, chemical formulas, and proper‐name tokens.

    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
    Cres
    -0.90
    ใด
    -0.90
     ventanas
    -0.82
    dziew
    -0.82
     kolek
    -0.82
     zna
    -0.80
    Nai
    -0.79
     dziew
    -0.79
    pentru
    -0.78
    ZIONE
    -0.77
    POSITIVE LOGITS
     extranjera
    0.89
     снова
    0.88
    nit
    0.85
    onalds
    0.82
    連絡
    0.81
     where
    0.81
    ardt
    0.80
     hjæl
    0.79
     antworte
    0.79
    int
    0.79
    Activations Density 0.101%

    No Known Activations