© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40889
    Prev
    Next
    INDEX
    Explanations

    testing actions

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

    This neuron fires on discourse‐marking or modal/adverbial connector words (e.g. “should,” “also,” “can,” “already,” “both,” etc.) across languages.

    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
     don
    -2.42
    4
    -2.27
    1
    -2.19
    9
    -1.91
     keine
    -1.90
     no
    -1.86
     not
    -1.83
    7
    -1.74
    8
    -1.69
    no
    -1.63
    POSITIVE LOGITS
     borbo
    2.03
    鋮
    1.99
    甞
    1.84
     גם
    1.79
     coloridas
    1.78
     parachoque
    1.77
    ufes
    1.73
     voorbeeld
    1.72
     Temos
    1.70
    xvii
    1.67
    Activations Density 0.026%

    No Known Activations