© 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. 84320
    Prev
    Next
    INDEX
    Explanations

    operations affected

    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
     också
    -1.50
     Often
    -1.36
     myös
    -1.34
     Sometimes
    -1.30
    Also
    -1.29
    𝗣
    -1.27
     intensely
    -1.23
    ụng
    -1.23
     also
    -1.19
     أيضا
    -1.19
    POSITIVE LOGITS
     its
    2.02
     jego
    1.43
    
    1.38
    ﮧ
    1.37
     لدي
    1.34
    ⅽ
    1.30
     afectados
    1.28
     will
    1.27
    啻
    1.27
    Its
    1.26
    Activations Density 0.189%

    No Known Activations