© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30703
    Prev
    Next
    INDEX
    Explanations

    is or are followed by current state

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

    The neuron specializes in spotting numeric values and statistics (e.g. raw numbers and figures) in the text.

    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
     these
    -0.99
    ILITY
    -0.94
     each
    -0.89
    RUNTIME
    -0.88
     diversos
    -0.88
    brtc
    -0.87
     which
    -0.86
    fications
    -0.84
     numerosas
    -0.84
    rophes
    -0.82
    POSITIVE LOGITS
     averaging
    1.04
     still
    1.03
     ranked
    1.02
     currently
    1.00
     in
    0.98
     tenth
    0.95
    Symp
    0.90
     fortfarande
    0.88
    日閲覧
    0.86
     Neighbors
    0.86
    Activations Density 0.026%

    No Known Activations