© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130988
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on phrases that describe what a tool or feature enables you to do—e.g. “allows you to,” “will let you,” and similar “enabling” constructions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    allows you to perform actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     other
    -1.70
     our
    -1.55
     some
    -1.53
     there
    -1.41
     providing
    -1.38
     being
    -1.37
     vigorous
    -1.33
     others
    -1.32
     siendo
    -1.30
     new
    -1.30
    POSITIVE LOGITS
     simpel
    1.55
     nejen
    1.55
     auffi
    1.48
     墊
    1.48
     serre
    1.45
     terrasse
    1.44
     Février
    1.42
     trône
    1.41
     mêmes
    1.40
     hommage
    1.39
    Activations Density 0.104%

    No Known Activations