© 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. 78604
    Prev
    Next
    INDEX
    Explanations

    CD changers

    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
    DataItem
    -0.80
    recie
    -0.75
     rezept
    -0.75
    zieli
    -0.73
     Смо
    -0.72
    Tabs
    -0.70
     Margo
    -0.69
    Capture
    -0.68
     Zlat
    -0.67
    capture
    -0.66
    POSITIVE LOGITS
     changer
    1.48
    changer
    1.38
     Changer
    1.37
     chang
    1.23
    Changer
    1.20
    Change
    1.20
    change
    1.16
     Change
    1.10
     change
    1.09
    changers
    1.07
    Activations Density 0.037%

    No Known Activations