© 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. 69998
    Prev
    Next
    INDEX
    Explanations

    spring

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

    The neuron specifically picks out numeric and punctuation sequences typical of scholarly citations (years, volume/issue numbers, page ranges, DOIs, 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
     ವ
    -0.83
     oxford
    -0.80
     Neustadt
    -0.77
    něž
    -0.76
    PROXY
    -0.75
    我还
    -0.74
    ådet
    -0.74
     Andrei
    -0.73
    teig
    -0.73
    ोक
    -0.72
    POSITIVE LOGITS
     Springer
    1.77
    Springer
    1.77
    springer
    1.50
     spring
    1.13
     Springs
    0.95
     springs
    0.91
    ᅟ
    0.87
     cofre
    0.84
    sighs
    0.82
    sprung
    0.81
    Activations Density 0.023%

    No Known Activations