© 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. 78568
    Prev
    Next
    INDEX
    Explanations

    GUI editing

    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
    раль
    -0.80
    IBAction
    -0.76
    Spons
    -0.71
    Seismic
    -0.71
     隔
    -0.69
    Faust
    -0.69
    orige
    -0.68
    Suspicious
    -0.67
    Modeling
    -0.66
     granular
    -0.66
    POSITIVE LOGITS
     UI
    2.06
    UI
    1.86
     ui
    1.80
     HUD
    1.72
     gui
    1.66
    ui
    1.63
     GUI
    1.61
     Ui
    1.54
    HUD
    1.51
    Ui
    1.49
    Activations Density 0.038%

    No Known Activations