© 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. 55804
    Prev
    Next
    INDEX
    Explanations

    file identifiers

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

    The neuron is triggered by numeric tokens (any standalone numbers, including version numbers, CSS values, identifiers, 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
    shared
    -0.69
    ulatum
    -0.69
     buffet
    -0.69
    "?>
    -0.67
     Canton
    -0.67
    hran
    -0.66
     MutableLiveData
    -0.65
    derung
    -0.65
    ット
    -0.64
    ươi
    -0.64
    POSITIVE LOGITS
     herhangi
    0.69
     親
    0.68
     propriety
    0.67
    ్యా
    0.66
     معنا
    0.65
    的确
    0.65
     PSV
    0.65
     zengin
    0.64
     GRACE
    0.64
     link
    0.63
    Activations Density 0.054%

    No Known Activations