© 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. 98735
    Prev
    Next
    INDEX
    Explanations

    Free Software Foundation

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

    The neuron is detecting numeric tokens (sequences of digits such as verse numbers, years, version numbers, etc.).

    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
     etc
    -0.90
     or
    -0.88
     it
    -0.86
     if
    -0.85
     },
    -0.84
    ,
    -0.80
     and
    -0.80
     __
    -0.79
    -0.77
    ละคร
    -0.77
    POSITIVE LOGITS
     profi
    0.97
    meldet
    0.97
     nett
    0.92
    勫
    0.91
     '${
    0.91
     デニム
    0.91
     '".$
    0.91
     verko
    0.90
     footed
    0.90
    読み
    0.89
    Activations Density 0.001%

    No Known Activations