© 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. 30905
    Prev
    Next
    INDEX
    Explanations

    custom class definitions

    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
     GridLayout
    -0.82
    존
    -0.80
     SQLException
    -0.80
     QWidget
    -0.78
    ieron
    -0.73
     頂
    -0.73
    roppo
    -0.73
     JFrame
    -0.73
    PropertyChanging
    -0.72
    ร์
    -0.71
    POSITIVE LOGITS
     my
    2.34
     My
    1.95
     Custom
    1.73
     custom
    1.70
    My
    1.70
    Custom
    1.52
    custom
    1.50
    my
    1.48
     MY
    1.47
     our
    1.43
    Activations Density 0.099%

    No Known Activations