© 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. 58212
    Prev
    Next
    INDEX
    Explanations

    boundaries and fours

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

    The neuron strongly activates on numeric tokens (years, measurements, counts, etc.), i.e. occurrences of numbers.

    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
     PRESENTATION
    -0.76
     motions
    -0.71
     stip
    -0.70
     presentation
    -0.69
     Presentation
    -0.68
     presentations
    -0.68
    ARTICLE
    -0.67
    вала
    -0.67
    Presentation
    -0.67
     ポイント
    -0.66
    POSITIVE LOGITS
     boundaries
    1.50
     boundary
    1.49
    boundary
    1.33
     Boundaries
    1.27
     Boundary
    1.23
    boundaries
    1.14
    Boundary
    1.14
    Boundaries
    1.13
    BOUND
    1.08
     fours
    1.06
    Activations Density 0.005%

    No Known Activations