© 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. 12496
    Prev
    Next
    INDEX
    Explanations

    proposing actions or changes

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

    This neuron fires on action-oriented words that introduce the aims or proposals of a research plan (e.g. verbs like “organize,” “create,” “propose,” “use,” “apply”).

    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
     этих
    -1.66
     these
    -1.51
    CONCLUSIONES
    -1.39
     diesen
    -1.30
     rassemb
    -1.27
     dessas
    -1.25
     destes
    -1.23
    these
    -1.23
    //!
    
    -1.20
     comparação
    -1.18
    POSITIVE LOGITS
     if
    1.90
     but
    1.83
     by
    1.72
     a
    1.70
     without
    1.68
     or
    1.58
     should
    1.58
     as
    1.50
     using
    1.42
     options
    1.42
    Activations Density 0.119%

    No Known Activations