© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68239
    Prev
    Next
    INDEX
    Explanations

    plural possessives or abbreviations )

    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
    One
    -1.72
    Only
    -1.46
     of
    -1.46
    First
    -1.45
     armées
    -1.43
     ดำ
    -1.41
    最初の
    -1.41
     pourra
    -1.36
    或
    -1.33
     WEBSITE
    -1.30
    POSITIVE LOGITS
    ).
    1.95
    を使用した
    1.70
     to
    1.70
     in
    1.67
    }})
    1.52
     drob
    1.52
     schönes
    1.50
     MediatR
    1.49
     klasa
    1.48
    筴
    1.48
    Activations Density 0.061%

    No Known Activations