© 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. 14408
    Prev
    Next
    INDEX
    Explanations

    dates back to

    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
    CURLOPT
    -1.80
     one
    -1.70
     a
    -1.57
     two
    -1.53
     there
    -1.47
    蹕
    -1.43
    leqslant
    -1.41
     Often
    -1.38
    鬭
    -1.35
    ՞
    -1.32
    POSITIVE LOGITS
     
    1.75
     månader
    1.75
    ↵
    1.68
    '
    1.56
     veckor
    1.52
    of
    1.45
     zaten
    1.45
     ähnliche
    1.42
    普通に
    1.41
     einschließlich
    1.41
    Activations Density 0.026%

    No Known Activations