© 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. 34-GEMMASCOPE-RES-131K
    7. 59198
    Prev
    Next
    INDEX
    Explanations

    URLs and citations

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

    The neuron selectively activates on numeric and punctuation tokens—especially digit sequences and URL/ID separators like “/”, “=”, and numbers.

    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
     even
    -0.96
     так
    -0.86
     barely
    -0.85
    ceres
    -0.79
     So
    -0.79
     niż
    -0.79
     úgy
    -0.78
     белье
    -0.77
     so
    -0.76
    عف
    -0.76
    POSITIVE LOGITS
    INTERVIEW
    0.88
    מון
    0.86
     ANI
    0.85
    իկ
    0.84
     asser
    0.84
    ָם
    0.84
    uminense
    0.83
    Dax
    0.83
     deta
    0.83
     corret
    0.82
    Activations Density 0.099%

    No Known Activations