© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32970
    Prev
    Next
    INDEX
    Explanations

    from another

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

    This neuron fires on documentation or comment text describing data transmission or communication actions (e.g. sending, receiving, accessing, and communicating with a component).

    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
     “
    -1.47
    igth
    -1.39
     exuber
    -1.36
     his
    -1.31
     flamboyant
    -1.29
     luscious
    -1.28
     revamped
    -1.27
     foll
    -1.27
     dando
    -1.27
     elegant
    -1.26
    POSITIVE LOGITS
     through
    1.45
     with
    1.41
     Comédie
    1.36
     or
    1.34
    🎆
    1.30
     within
    1.30
     system
    1.29
    🤠
    1.27
     Although
    1.25
    رها
    1.23
    Activations Density 0.081%

    No Known Activations