© 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. 60576
    Prev
    Next
    INDEX
    Explanations

    place names followed by clauses

    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
     for
    -1.34
     like
    -1.02
    endalikan
    -0.99
     jsou
    -0.98
     älskar
    -0.95
     somewhere
    -0.95
    子さん
    -0.95
    不
    -0.94
     Monday
    -0.94
     Tuesday
    -0.93
    POSITIVE LOGITS
     which
    3.48
     that
    3.16
     التي
    1.88
     where
    1.73
     wherein
    1.71
     والتي
    1.62
     که
    1.59
     waarin
    1.54
     whereby
    1.52
     الذي
    1.49
    Activations Density 0.118%

    No Known Activations