© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93688
    Prev
    Next
    INDEX
    Explanations

    past tense verb endings and participles

    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_34/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
    cún
    -1.21
    j
    -1.08
    _
    -1.08
    為に
    -1.05
     Incluso
    -1.02
     împreună
    -1.02
    damit
    -1.01
    R
    -1.00
     pentru
    -0.99
    estries
    -0.99
    POSITIVE LOGITS
     granat
    1.47
     umy
    1.41
     bluz
    1.39
     icône
    1.35
     luks
    1.31
     kuchen
    1.30
     ones
    1.26
    lardan
    1.25
     ANOTHER
    1.25
     eki
    1.24
    Activations Density 0.004%

    No Known Activations