© 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. 63160
    Prev
    Next
    INDEX
    Explanations

    lines parallel

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

    The neuron fires on numeric references—digits or number words—especially in technical or mathematical contexts.

    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
    checklist
    -0.83
     xml
    -0.81
    裾
    -0.75
    ын
    -0.73
     Söhne
    -0.73
     yüzük
    -0.71
     számára
    -0.71
     SCIENTIFIC
    -0.71
     disminución
    -0.70
    瓣
    -0.70
    POSITIVE LOGITS
     lines
    1.72
     line
    1.43
     Lines
    1.31
    Lines
    1.30
    lines
    1.30
    Line
    1.20
    line
    1.16
    LINES
    1.07
     LINE
    1.07
    LINE
    1.05
    Activations Density 0.031%

    No Known Activations