© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76773
    Prev
    Next
    INDEX
    Explanations

    size and scale

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

    The neuron strongly activates on numeric tokens and measurement values (e.g. digits representing counts, sizes, or quantities).

    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
    越高
    -0.92
    zęd
    -0.88
     velocidades
    -0.84
    高度
    -0.83
     quos
    -0.78
    ต่
    -0.77
     quæ
    -0.76
    сная
    -0.74
    يقة
    -0.74
    tionally
    -0.73
    POSITIVE LOGITS
     large
    6.19
     larger
    5.38
    large
    4.88
     bigger
    4.44
    Large
    4.31
    larger
    4.13
     largest
    4.00
     LARGE
    3.98
     big
    3.97
    LARGE
    3.92
    Activations Density 0.612%

    No Known Activations