© 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. 22-GEMMASCOPE-RES-131K
    7. 35238
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions

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

    This neuron detects inflected action verbs (third‐person singular present or past tense) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     włosów
    -1.23
    entieth
    -1.22
    راهن
    -1.16
    żna
    -1.16
     posteriore
    -1.15
     saisi
    -1.15
     hés
    -1.14
     coger
    -1.13
    ambut
    -1.12
    壠
    -1.11
    POSITIVE LOGITS
     also
    1.81
    r
    1.20
     أيضا
    1.17
    d
    1.16
    bo
    1.15
    b
    1.14
    c
    1.14
    te
    1.13
    g
    1.09
    la
    1.08
    Activations Density 0.138%

    No Known Activations