© 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. 86705
    Prev
    Next
    INDEX
    Explanations

    names and introductory phrases

    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
    Zubereitung
    -1.44
    <bos>
    -1.39
    tifice
    -1.33
    Merkmale
    -1.29
     to
    -1.29
    を中心に
    -1.27
     who
    -1.26
     demnach
    -1.22
    ghest
    -1.20
    IFORNIA
    -1.19
    POSITIVE LOGITS
     their
    1.21
    </strong>
    1.20
     Tomaten
    1.19
    création
    1.14
     or
    1.13
     مختلف
    1.12
     konu
    1.11
    其
    1.11
    zionali
    1.10
     organismes
    1.09
    Activations Density 0.142%

    No Known Activations