© 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. 34-GEMMASCOPE-RES-131K
    7. 66268
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by record labels

    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
    watching
    -0.79
    exprimer
    -0.79
     รุ่น
    -0.75
    ordion
    -0.75
    ghton
    -0.73
    ACTS
    -0.72
    otation
    -0.72
    cuta
    -0.71
     grupper
    -0.71
    PDF
    -0.70
    POSITIVE LOGITS
     Warner
    2.63
    Warner
    2.30
     Universal
    2.11
     Sony
    1.94
     Columbia
    1.81
     EMI
    1.77
    Universal
    1.68
    Columbia
    1.55
    Sony
    1.54
     RCA
    1.49
    Activations Density 0.140%

    No Known Activations