© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41300
    Prev
    Next
    INDEX
    Explanations

    part of

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

    The neuron fires on words denoting a component or subdivision of something (e.g. “part,” “portion,” “section”).

    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
     as
    -2.11
     for
    -1.97
     any
    -1.78
     their
    -1.70
    (!__
    -1.67
     an
    -1.66
     a
    -1.57
     to
    -1.45
     ANY
    -1.37
     amelyek
    -1.37
    POSITIVE LOGITS
     multicolore
    1.45
    コンパクト
    1.43
    とはいえ
    1.42
    あっという間に
    1.41
     infinita
    1.37
     作り方
    1.37
    的時候
    1.35
    さぁ
    1.34
     alimenti
    1.34
    ta
    1.34
    Activations Density 0.099%

    No Known Activations