© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113668
    Prev
    Next
    INDEX
    Explanations

    verbs indicating state or completion

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

    This neuron responds to technical or formal action verbs in the past participle (–ed) form, as used in passive or procedural descriptions.

    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
     mereka
    -1.40
    بیش
    -1.33
    طراحی
    -1.30
     *)&
    -1.30
    }}</
    -1.27
    بدون
    -1.27
    افز
    -1.26
     ними
    -1.25
    Ende
    -1.23
    ığım
    -1.23
    POSITIVE LOGITS
    in
    1.55
     in
    1.22
    [
    1.20
     it
    1.12
     things
    1.10
    ヒト
    1.06
     elements
    1.06
    ↵↵
    1.05
      
    1.02
     again
    0.98
    Activations Density 0.287%

    No Known Activations