© 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. 3066
    Prev
    Next
    INDEX
    Explanations

    navigation and controllers

    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
    คุ
    -0.77
    curs
    -0.73
    
    -0.69
     Brum
    -0.69
     Omb
    -0.68
    VISED
    -0.68
    ٛ
    -0.68
    RemoveAt
    -0.67
    mės
    -0.67
    激情
    -0.66
    POSITIVE LOGITS
     nav
    1.34
    Nav
    1.22
    Ctrl
    1.08
     Nav
    1.07
    nav
    1.03
    NAV
    0.94
    events
    0.94
     Ctrl
    0.91
     plt
    0.91
    params
    0.91
    Activations Density 0.008%

    No Known Activations