© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20247
    Prev
    Next
    INDEX
    Explanations

    javadoc, CET, Stone Age

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

    The neuron is sensitive to numeric tokens (numbers and version‐style digits).

    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
     corriger
    -2.02
     ſp
    -1.87
     etek
    -1.84
     türkiye
    -1.80
     interesses
    -1.79
    !!!!!!!
    -1.76
     ſen
    -1.76
     pérd
    -1.74
     !!!!
    -1.73
     diki
    -1.73
    POSITIVE LOGITS
     with
    2.28
     including
    1.97
     While
    1.77
     не
    1.77
     was
    1.74
     still
    1.70
     in
    1.66
    Beskrivning
    1.65
     from
    1.63
     had
    1.63
    Activations Density 0.000%

    No Known Activations