© 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. 10-GEMMASCOPE-RES-131K
    7. 7533
    Prev
    Next
    INDEX
    Explanations

    magnitude of quantity

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

    The neuron strongly activates on occurrences of the word “magnitude” (and its associated numeric values) in technical or scientific 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_10/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
    ㆆ
    -2.69
    y
    -2.63
    ꜆
    -2.53
     adage
    -2.33
     futile
    -2.31
     tuvimos
    -2.31
     revolved
    -2.28
    penuhi
    -2.28
     drawback
    -2.27
    Mittwoch
    -2.27
    POSITIVE LOGITS
     and
    3.00
     of
    2.44
    .
    2.31
    <bos>
    2.27
     
    2.17
    </sup>
    2.03
    ↵
    2.02
    驁
    1.97
     obtener
    1.94
    ſſen
    1.92
    Activations Density 0.002%

    No Known Activations