© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73138
    Prev
    Next
    INDEX
    Explanations

    size, width, and height

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

    The neuron activates on numeric tokens—numbers and measurements 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_22/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
     what
    -0.90
     all
    -0.87
    ),
    -0.87
    言った
    -0.87
    その後
    -0.85
    clr
    -0.85
     then
    -0.84
    Firstly
    -0.84
    ែ
    -0.84
    それでも
    -0.82
    POSITIVE LOGITS
     size
    1.89
     sizes
    1.62
    size
    1.57
    setSize
    1.31
     widths
    1.27
     width
    1.20
    length
    1.20
    MergeFrom
    1.17
     Size
    1.16
     length
    1.12
    Activations Density 0.020%

    No Known Activations