© 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. 10-GEMMASCOPE-RES-131K
    7. 65901
    Prev
    Next
    INDEX
    Explanations

    foreign words and symbols

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

    The neuron fires on numeric literal tokens (unquoted numbers) embedded in JSON‐like structures.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Our
    -1.80
    as
    -1.66
    We
    -1.66
    its
    -1.57
     хоте
    -1.55
     still
    -1.48
    }
    -1.44
    When
    -1.43
     już
    -1.43
     it
    -1.41
    POSITIVE LOGITS
     -¿
    2.05
    
    1.77
     Некоторые
    1.73
     alguns
    1.70
    ଃ
    1.69
     vários
    1.65
     algunos
    1.64
     certains
    1.61
     哪些
    1.59
     ſever
    1.59
    Activations Density 0.016%

    No Known Activations