© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1538
    Prev
    Next
    INDEX
    Explanations

    dialog titles and confirmations

    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
     menu
    -0.98
    Menu
    -0.88
    menu
    -0.79
     Menu
    -0.79
    andri
    -0.78
     меню
    -0.77
     menus
    -0.75
    antMatchers
    -0.74
     április
    -0.74
     perspective
    -0.74
    POSITIVE LOGITS
     OK
    2.30
     ok
    1.95
    OK
    1.87
     Ok
    1.77
     okay
    1.70
    Ok
    1.64
    DialogResult
    1.59
    ok
    1.45
     alright
    1.42
     accepted
    1.36
    Activations Density 0.019%

    No Known Activations