© 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. 86803
    Prev
    Next
    INDEX
    Explanations

    reading and reader

    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
     biên
    -0.90
     lernen
    -0.85
     obje
    -0.78
     pikiran
    -0.76
     songwriting
    -0.74
     whirlwind
    -0.74
     mesta
    -0.73
    vod
    -0.71
     আ
    -0.71
     Zing
    -0.70
    POSITIVE LOGITS
     reading
    1.84
     Reading
    1.35
    Reading
    1.34
     чита
    1.23
     reader
    1.22
    reading
    1.19
     olvas
    1.18
    อ่าน
    1.17
     read
    1.16
     pleasure
    1.10
    Activations Density 0.017%

    No Known Activations