© 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. 33463
    Prev
    Next
    INDEX
    Explanations

    state of being or action

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

    The neuron is picking out open-class “content” words (nouns and verbs) rather than function or stop 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
    obviously
    -1.50
     gewi
    -1.36
    extremely
    -1.35
     faciliter
    -1.33
     adesivo
    -1.31
     spektak
    -1.29
    basically
    -1.27
     Sahne
    -1.25
     strukt
    -1.25
     ROBERT
    -1.25
    POSITIVE LOGITS
     with
    1.44
     started
    1.42
     went
    1.32
     despite
    1.32
     or
    1.27
     although
    1.27
     took
    1.25
     began
    1.23
     even
    1.23
     described
    1.18
    Activations Density 0.036%

    No Known Activations