© 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. 65888
    Prev
    Next
    INDEX
    Explanations

    stir and stirring

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

    The neuron strongly activates on the various inflected forms of the verb “stir” (e.g. stir, stirring, stirs).

    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
    er
    -2.73
    4
    -2.44
    뭄
    -2.41
    ᎒
    -2.39
    with
    -2.38
    或者
    -2.30
    ﹍﹍
    -2.23
    
    -2.22
    tillerie
    -2.17
     نکنید
    -2.14
    POSITIVE LOGITS
    」(
    2.39
    翃
    2.33
    逦
    2.30
    
    2.23
    o
    2.14
     recommending
    2.08
    archiwizowane
    2.06
    </h3>
    2.05
     ukrain
    2.05
     fazia
    2.03
    Activations Density 0.003%

    No Known Activations