© 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. 10-GEMMASCOPE-RES-131K
    7. 129506
    Prev
    Next
    INDEX
    Explanations

    dispersion

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

    The neuron consistently activates on the word “dispersion” (and close variants) in scientific contexts, i.e. it detects mentions of dispersion.

    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
    嘥
    -2.91
     persino
    -2.86
     メニュー
    -2.80
    Ꮉ
    -2.69
    瀦
    -2.66
    ᠌
    -2.58
     sorgfäl
    -2.56
    ⎚
    -2.55
    輒
    -2.52
    镚
    -2.52
    POSITIVE LOGITS
    o
    2.94
    ):
    2.91
    e
    2.83
    …
    2.63
    ed
    2.59
    ;
    2.50
     …
    2.30
    y
    2.25
    <em>
    2.22
    ]
    2.20
    Activations Density 0.004%

    No Known Activations