© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 48827
    Prev
    Next
    INDEX
    Explanations

    past tense auxiliary verbs

    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
    美味しいです
    -1.95
     are
    -1.61
     is
    -1.56
     છે
    -1.52
     shes
    -1.50
    Been
    -1.47
    ствуют
    -1.38
     antworte
    -1.32
    trusive
    -1.31
    зывают
    -1.29
    POSITIVE LOGITS
     was
    6.19
     had
    3.70
     were
    3.63
     could
    3.41
     would
    3.36
     وكان
    3.34
     wasn
    3.30
     было
    3.20
     была
    3.13
     ήταν
    3.03
    Activations Density 0.383%

    No Known Activations