© 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. 129383
    Prev
    Next
    INDEX
    Explanations

    better followed by verb or adjective

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

    The neuron is picking out directive or imperative verbs used to give advice, commands, or instructions.

    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
     perpé
    -1.44
     probablement
    -1.38
     voi
    -1.34
    合わせる
    -1.34
     ananas
    -1.33
    ⍢
    -1.33
     zove
    -1.32
    푘
    -1.30
     kalan
    -1.30
    噲
    -1.30
    POSITIVE LOGITS
     if
    1.70
     before
    1.46
     with
    1.41
     him
    1.41
    3
    1.41
     than
    1.36
     at
    1.35
     piuttosto
    1.34
     rather
    1.34
    6
    1.32
    Activations Density 0.024%

    No Known Activations