© 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. 63342
    Prev
    Next
    INDEX
    Explanations

    section titles or dividers

    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
    чие
    -0.81
    IVERSITY
    -0.75
     национа
    -0.75
     iran
    -0.71
     februari
    -0.71
    ḷ
    -0.71
     oxidative
    -0.71
     immigrant
    -0.71
    //*
    -0.69
    
    -0.69
    POSITIVE LOGITS
     border
    0.97
     separated
    0.90
    اريخ
    0.89
    divided
    0.84
     halves
    0.82
     cross
    0.81
     divided
    0.81
     crossing
    0.80
     зоне
    0.79
     hotline
    0.78
    Activations Density 0.010%

    No Known Activations