© 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. 22-GEMMASCOPE-RES-131K
    7. 33921
    Prev
    Next
    INDEX
    Explanations

    Star Awards

    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_22/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
     why
    -1.16
     everything
    -1.06
     Everything
    -1.02
    :
    -0.95
     Behaup
    -0.89
     おり
    -0.89
     lernen
    -0.88
    それぞれの
    -0.87
    onner
    -0.87
    ipan
    -0.87
    POSITIVE LOGITS
    Ār
    1.11
    CRIPTION
    0.98
     प्रोड
    0.98
    ような
    0.93
     アイド
    0.93
    anolamine
    0.88
    شارة
    0.87
     vinyle
    0.86
    ffekt
    0.85
    دانلود
    0.85
    Activations Density 0.001%

    No Known Activations