© 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. 63461
    Prev
    Next
    INDEX
    Explanations

    code, project files, and modules

    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
     even
    -0.98
     said
    -0.94
    ｪ
    -0.93
     ==
    -0.89
     this
    -0.86
     because
    -0.86
     especially
    -0.86
     finally
    -0.85
     like
    -0.84
     says
    -0.83
    POSITIVE LOGITS
     spiele
    0.95
    纔
    0.93
     teile
    0.91
    
    0.90
    🤟
    0.90
     onely
    0.89
     boden
    0.88
    donc
    0.87
    recht
    0.86
     morgen
    0.86
    Activations Density 0.003%

    No Known Activations