© 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. 118358
    Prev
    Next
    INDEX
    Explanations

    reading completed or ongoing

    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
    сім
    -0.77
     לְ
    -0.72
    ità
    -0.72
    Ք
    -0.71
    хин
    -0.71
    apunov
    -0.70
    <0x82>
    -0.68
    ്
    -0.68
    ктория
    -0.67
    identiality
    -0.67
    POSITIVE LOGITS
     read
    7.25
     reading
    6.50
     reads
    5.22
    read
    5.00
    reading
    4.50
    Reading
    4.47
     đọc
    4.25
    读
    4.22
     чита
    4.19
     readings
    4.16
    Activations Density 0.278%

    No Known Activations