© 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. 22-GEMMASCOPE-RES-131K
    7. 128480
    Prev
    Next
    INDEX
    Explanations

    UI elements and code syntax

    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_22/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
    Also
    -1.16
    Consequently
    -1.07
    analysis
    -1.02
     consequence
    -1.00
    ûte
    -0.99
     були
    -0.98
    場所に
    -0.98
     також
    -0.96
    those
    -0.96
    gebnisse
    -0.96
    POSITIVE LOGITS
    ╚
    1.05
    
    0.99
     right
    0.98
     BAY
    0.97
     Ministero
    0.97
     barran
    0.96
    ₂)
    0.94
     ilegal
    0.93
    )];
    0.92
    ;->
    0.90
    Activations Density 0.000%

    No Known Activations