© 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. 66284
    Prev
    Next
    INDEX
    Explanations

    reading and books

    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
     Cochrane
    -0.97
    蹈
    -0.93
    ği
    -0.92
    watchers
    -0.88
     documentos
    -0.88
     לְ
    -0.88
    viä
    -0.88
    ToFile
    -0.88
     "+
    -0.84
    rawDesc
    -0.84
    POSITIVE LOGITS
     reread
    2.17
     reading
    2.02
     read
    1.94
    Reading
    1.46
     lettura
    1.43
     recommend
    1.43
     unread
    1.42
     reads
    1.41
     recommending
    1.40
    reading
    1.36
    Activations Density 0.063%

    No Known Activations