© 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. 58941
    Prev
    Next
    INDEX
    Explanations

    verbs ending in -ing

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

    This neuron fires on titles or headings that begin with a “-ing” verb (a gerund or present participle).

    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
     ABBREVIATIONS
    -1.50
    大气
    -1.38
    犼
    -1.36
    劇情
    -1.34
    们的
    -1.34
    齜
    -1.33
    荦
    -1.33
     heats
    -1.32
     diputados
    -1.31
     gobiernos
    -1.30
    POSITIVE LOGITS
    ánicos
    1.44
     thwart
    1.35
    眼下
    1.26
     While
    1.26
     véritable
    1.25
    ategorie
    1.25
     all
    1.25
    ž
    1.23
    ).”
    1.22
     During
    1.20
    Activations Density 0.039%

    No Known Activations