© 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. 65695
    Prev
    Next
    INDEX
    Explanations

    development tutorials migration

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

    The neuron strongly activates on isolated digits and dots—i.e. numeric tokens (especially version‐number strings like “1.0”) in XML/DTD/plist markup.

    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
     boek
    -0.84
     Jurist
    -0.83
     sebastian
    -0.82
     flesta
    -0.81
    storms
    -0.79
     antonio
    -0.78
    Bibliografia
    -0.77
     Ла
    -0.76
    Church
    -0.75
     joel
    -0.75
    POSITIVE LOGITS
    賤
    0.89
    Ena
    0.82
    足を
    0.80
     aceler
    0.79
    τι
    0.78
    ค์
    0.78
     sitting
    0.77
    ների
    0.77
     digging
    0.76
    смотра
    0.75
    Activations Density 0.004%

    No Known Activations