© 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. 34-GEMMASCOPE-RES-131K
    7. 48730
    Prev
    Next
    INDEX
    Explanations

    io.Reader or Read

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

    This neuron detects occurrences of the “io” identifier (especially in import paths or package names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     У
    -0.78
    external
    -0.77
    gen
    -0.69
     zewnętr
    -0.69
    minus
    -0.69
     external
    -0.69
    olar
    -0.69
     honesty
    -0.69
    śl
    -0.67
     μή
    -0.67
    POSITIVE LOGITS
     reader
    2.13
     readers
    1.84
     Readers
    1.76
    reader
    1.73
     Reader
    1.66
    Readers
    1.62
    Reader
    1.58
    readers
    1.57
     READER
    1.47
     io
    1.30
    Activations Density 0.039%

    No Known Activations