© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    opening dialogs and navigation

    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
     glaubte
    -0.84
    ₲
    -0.77
     DataLoader
    -0.74
    
    -0.71
    aneta
    -0.71
     szí
    -0.71
    lapsed
    -0.71
    illah
    -0.69
    nehå
    -0.69
     khoe
    -0.69
    POSITIVE LOGITS
    Dialog
    0.91
     dialog
    0.84
     MatDialog
    0.83
     modal
    0.83
    Ref
    0.80
    弹出
    0.79
     jist
    0.78
     openers
    0.78
    demort
    0.78
     Dialog
    0.77
    Activations Density 0.009%

    No Known Activations