© 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. 10919
    Prev
    Next
    INDEX
    Explanations

    first-hand experience and knowledge

    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
     there
    -1.57
     جديدة
    -1.27
    يون
    -1.26
     Revista
    -1.23
     they
    -1.22
    pekte
    -1.21
     tentang
    -1.20
     Excellent
    -1.18
     amiga
    -1.18
     knight
    -1.16
    POSITIVE LOGITS
     also
    1.38
     kwamba
    1.38
     également
    1.34
    wasn
    1.34
    data
    1.30
    knows
    1.29
     الذي
    1.28
    呿
    1.28
    ехали
    1.24
     komplette
    1.23
    Activations Density 0.050%

    No Known Activations