© 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. 34-GEMMASCOPE-RES-131K
    7. 117396
    Prev
    Next
    INDEX
    Explanations

    android xml

    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_34/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
     highlighted
    -0.88
    维
    -0.79
     continual
    -0.79
     longstanding
    -0.79
     more
    -0.78
     highlighting
    -0.77
    وامل
    -0.77
    异
    -0.76
     severely
    -0.75
     exquisitely
    -0.75
    POSITIVE LOGITS
     produtos
    1.02
     tinha
    0.96
     ficou
    0.91
     페이지
    0.90
     Había
    0.87
    ffled
    0.86
     jogos
    0.85
     trois
    0.85
    誂
    0.85
     JAXB
    0.85
    Activations Density 0.049%

    No Known Activations