© 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. 10-GEMMASCOPE-RES-131K
    7. 38973
    Prev
    Next
    INDEX
    Explanations

    Honolulu, Slovak, subclasses

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

    The neuron selectively activates on German conjugated verbs (notably the modal verbs “kann,” “soll,” and “spricht”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    聼
    -3.16
    宬
    -3.09
    荩
    -2.98
    鹉
    -2.91
    锱
    -2.86
    
    -2.84
    쨩
    -2.80
    ܊
    -2.77
    汌
    -2.75
    
    -2.73
    POSITIVE LOGITS
    e
    4.34
    as
    3.41
    in
    3.22
    a
    2.89
     
    2.89
    на
    2.83
    ing
    2.70
    it
    2.69
    er
    2.66
     We
    2.63
    Activations Density 0.002%

    No Known Activations