© 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. 2861
    Prev
    Next
    INDEX
    Explanations

    clothing parts and code syntax

    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
    gains
    -0.98
     Gains
    -0.85
    sejarah
    -0.84
     gains
    -0.80
    костюм
    -0.79
    他們
    -0.77
    moss
    -0.76
    wallpapers
    -0.76
    长老
    -0.75
    tires
    -0.75
    POSITIVE LOGITS
    +"/"+
    1.02
     legs
    0.98
    ("."
    0.94
     lenses
    0.90
     leg
    0.90
    ('.'
    0.86
     crotch
    0.84
     '['
    0.82
     flexibility
    0.81
     cups
    0.81
    Activations Density 0.032%

    No Known Activations