© 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. 34096
    Prev
    Next
    INDEX
    Explanations

    President Barack Obama

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

    The neuron predominantly fires on numeric tokens (digits, numeric values) and related punctuation (e.g. parentheses or quotes around numbers).

    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
     one
    -1.52
     in
    -1.47
     on
    -1.46
     as
    -1.43
     without
    -1.42
     can
    -1.41
     at
    -1.40
     two
    -1.38
     mainly
    -1.30
     undeniably
    -1.30
    POSITIVE LOGITS
    カッコいい
    1.27
    素晴らしい
    1.27
    色んな
    1.27
    あっという間に
    1.23
     এবং
    1.23
    色々な
    1.23
    かっこ
    1.22
     siè
    1.22
    かっこいい
    1.20
    久し
    1.19
    Activations Density 0.087%

    No Known Activations