© 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. 78552
    Prev
    Next
    INDEX
    Explanations

    Licensed disclaimer cause

    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
    土豆
    -0.84
    jScrollPane
    -0.83
     siècle
    -0.77
    彬
    -0.73
     calculation
    -0.73
     clotting
    -0.72
    ぷ
    -0.71
     jars
    -0.71
     Evans
    -0.70
    commons
    -0.69
    POSITIVE LOGITS
    Expand
    1.08
     expand
    1.04
     expandir
    0.97
     expands
    0.96
    Nis
    0.94
     Expand
    0.93
    expansion
    0.89
    expand
    0.88
     expanded
    0.86
    Hc
    0.84
    Activations Density 0.016%

    No Known Activations