© 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. 78936
    Prev
    Next
    INDEX
    Explanations

    curly braces and quotes

    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
    liśmy
    -0.98
    nipeg
    -0.97
     daban
    -0.96
    corbic
    -0.95
     its
    -0.95
    になれる
    -0.94
    //{
    -0.93
    vrigt
    -0.93
    戰鬥
    -0.92
    >//
    -0.91
    POSITIVE LOGITS
     “
    1.48
     "
    1.48
     รวม
    1.23
     También
    1.11
     consi
    1.07
     spearheaded
    1.06
     ___________
    1.05
     ____________
    1.03
    makes
    1.02
     malgré
    1.00
    Activations Density 0.020%

    No Known Activations