© 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. 63738
    Prev
    Next
    INDEX
    Explanations

    point margin

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

    The neuron is a strong detector for numeric tokens (i.e. sequences of digits or numbers) 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
     left
    -3.05
    left
    -2.59
     Left
    -2.36
    Left
    -2.33
    LEFT
    -1.96
     LEFT
    -1.88
    左
    -1.84
    getLeft
    -1.82
    setLeft
    -1.60
     top
    -1.57
    POSITIVE LOGITS
     point
    2.08
     Point
    2.06
    Point
    2.00
     points
    1.84
     POINT
    1.66
    point
    1.65
    ポイント
    1.62
     Points
    1.55
    POINT
    1.46
    points
    1.31
    Activations Density 0.055%

    No Known Activations