© 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. 70068
    Prev
    Next
    INDEX
    Explanations

    NY Slip Op, lymphoid neoplasms

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

    legal document formatting and programming error messages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specialized to pick out digit‐containing tokens—numbers, version or reference IDs, dates, “Slip Op” citation numbers, error codes, 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
     ICS
    -0.76
     Coz
    -0.73
    herbe
    -0.73
     Equi
    -0.70
    Galaxy
    -0.69
    intre
    -0.68
     IDLE
    -0.68
     cheveux
    -0.68
     gangs
    -0.68
    amenta
    -0.68
    POSITIVE LOGITS
     Lokales
    0.77
    Hea
    0.72
     cuotas
    0.71
    LocalizedString
    0.68
     executives
    0.66
     Martini
    0.65
     heavily
    0.65
     synthetic
    0.63
    布局
    0.63
     mount
    0.63
    Activations Density 0.047%

    No Known Activations