© 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. 22-GEMMASCOPE-RES-131K
    7. 33772
    Prev
    Next
    INDEX
    Explanations

    descriptions of objects or qualities

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

    The neuron fires on substantive content words (key nouns and verbs) rather than on function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     vâ
    -1.35
    🤨
    -1.34
    🤮
    -1.32
    😯
    -1.30
    🤢
    -1.30
    😵
    -1.29
    😖
    -1.27
    ffed
    -1.26
    😣
    -1.23
    🫣
    -1.22
    POSITIVE LOGITS
    !
    1.48
     you
    1.45
     nosso
    1.39
    になれば
    1.33
    ようになりました
    1.28
     
    1.26
    ようです
    1.23
    兩
    1.22
     our
    1.19
    <b>
    1.17
    Activations Density 0.120%

    No Known Activations