© 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. 234
    Prev
    Next
    INDEX
    Explanations

    family, location, or affiliation

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

    The neuron fires on words that signal personal association or belonging (e.g. “own,” “hometown,” “favourite,” “assignee,” “electorate”).

    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
     REALLY
    -1.19
     remarkably
    -1.14
     .......
    -1.13
     predominantly
    -1.09
    ౨
    -1.08
     amazingly
    -1.08
     .........
    -1.06
     EVEN
    -1.06
     ridiculously
    -1.05
     ludicrous
    -1.05
    POSITIVE LOGITS
     on
    1.39
     as
    1.37
     from
    1.34
     at
    1.33
     so
    1.26
     in
    1.23
     over
    1.23
     if
    1.20
     one
    1.17
     before
    1.12
    Activations Density 0.037%

    No Known Activations