© 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. 10-GEMMASCOPE-RES-131K
    7. 65536
    Prev
    Next
    INDEX
    Explanations

    pagination and page numbering

    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_10/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
     about
    -1.59
     veh
    -1.36
     ὁ
    -1.34
    etna
    -1.29
     —
    -1.29
     maneiras
    -1.23
    踭
    -1.23
     Infór
    -1.20
    cademic
    -1.19
    enaar
    -1.18
    POSITIVE LOGITS
    排行
    1.50
     rate
    1.41
    Kommentare
    1.38
    '
    1.26
    気温
    1.25
     superare
    1.21
     imaginación
    1.21
     it
    1.20
     dibutuhkan
    1.20
    Dopo
    1.19
    Activations Density 0.016%

    No Known Activations