© 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. 71211
    Prev
    Next
    INDEX
    Explanations

    listView, eatery, artifactId

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

    This neuron picks out the single key noun or named entity that’s the focus of each snippet (e.g. the main class/component name in code or the principal subject noun in prose).

    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
    ',
    -3.13
    -3.00
    '
    -2.78
    0
    -2.56
     और
    -2.42
    A
    -2.39
    使用
    -2.25
    ",
    -2.22
     “
    -2.19
    可能
    -2.17
    POSITIVE LOGITS
    谖
    2.84
    悫
    2.56
    跸
    2.53
     we
    2.48
    峁
    2.39
    ’).
    2.33
    全都
    2.31
    犼
    2.30
    鷂
    2.30
    ’;
    2.23
    Activations Density 0.003%
    No Known Activations