© 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. 106847
    Prev
    Next
    INDEX
    Explanations

    section markers or code separators

    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
    guió
    -0.83
     Interpretation
    -0.81
    ANNE
    -0.77
     accompaniment
    -0.76
     interpretation
    -0.75
    سا
    -0.75
    subtitle
    -0.73
    Tham
    -0.73
    ospel
    -0.73
    неопр
    -0.72
    POSITIVE LOGITS
    鸞
    0.80
     Arial
    0.80
     السياس
    0.76
    fié
    0.75
     nhạc
    0.75
     Grüsse
    0.74
    diabetic
    0.74
    /]
    0.74
    FlatStyle
    0.73
    भव
    0.73
    Activations Density 0.001%

    No Known Activations