© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11598
    Prev
    Next
    INDEX
    Explanations

    verbs of action and occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     what
    -1.53
     such
    -1.38
    Following
    -1.34
     isComment
    -1.31
     caos
    -1.30
    What
    -1.28
    maphore
    -1.23
    rías
    -1.23
    żeli
    -1.23
     oscu
    -1.19
    POSITIVE LOGITS
     fanns
    1.60
     känns
    1.57
    -:
    1.55
    非常的
    1.53
     inalámbrico
    1.52
     ۱۲
    1.50
     huile
    1.45
    ronesia
    1.42
     Entfer
    1.41
     verletzt
    1.39
    Activations Density 0.127%

    No Known Activations