© 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. 116085
    Prev
    Next
    INDEX
    Explanations

    publisher names

    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
     but
    -0.88
    曲を
    -0.87
     wesentlichen
    -0.86
    曲は
    -0.77
     Once
    -0.74
    一旦
    -0.74
     SEDS
    -0.74
    日記
    -0.74
     core
    -0.73
    Generally
    -0.73
    POSITIVE LOGITS
     publishers
    1.74
     publishing
    1.68
     Publishing
    1.63
     publisher
    1.49
     Books
    1.45
     Verlag
    1.40
     Press
    1.36
    Verlag
    1.36
     Publications
    1.33
     Publisher
    1.33
    Activations Density 0.034%

    No Known Activations