© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7526
    Prev
    Next
    INDEX
    Explanations

    No. number period

    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
     皇族
    -1.42
    Aj
    -1.25
     différent
    -1.22
     прекрасно
    -1.21
    在中国
    -1.19
    ıla
    -1.18
     what
    -1.15
    臯
    -1.12
    澌
    -1.12
     océ
    -1.12
    POSITIVE LOGITS
     ilyen
    1.55
     at
    1.48
     there
    1.29
     kuten
    1.29
     böyle
    1.28
     From
    1.27
    》，
    1.23
    」，
    1.22
     they
    1.20
     время
    1.18
    Activations Density 0.211%

    No Known Activations