© 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. 13204
    Prev
    Next
    INDEX
    Explanations

    distribution of

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

    The neuron fires on scientific mentions of “distribution of … in …” phrases—that is, when a text is presenting measured distributions (e.g. “distribution of X in Y”).

    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
    糴
    -2.39
    nicity
    -2.36
    
    -2.34
    aneers
    -2.28
    </i>
    -2.19
    蓠
    -2.19
    鹚
    -2.16
    issory
    -2.13
    ulism
    -2.06
    ;
    -2.05
    POSITIVE LOGITS
    “
    2.03
     in
    1.90
     on
    1.84
    at
    1.80
    '
    1.76
     londres
    1.72
     ambayo
    1.66
     méxico
    1.58
     decently
    1.54
     málaga
    1.51
    Activations Density 0.037%

    No Known Activations