© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65849
    Prev
    Next
    INDEX
    Explanations

    Kern County, Kernberg, ECMAScript, ECM

    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
     Süden
    -2.50
    .
    -2.47
    2
    -2.41
     besonderer
    -2.22
     Erwart
    -2.22
    鲀
    -2.19
     Geschä
    -2.16
     outburst
    -2.13
    %,
    -2.11
     сначала
    -2.11
    POSITIVE LOGITS
     lancia
    2.56
    ⁉
    2.44
    寕
    2.36
     lanka
    2.33
    zeichneten
    2.30
     continúas
    2.25
    ﹕
    2.23
    ~•
    2.23
    es
    2.22
    荦
    2.19
    Activations Density 0.019%

    No Known Activations