© 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. 64992
    Prev
    Next
    INDEX
    Explanations

    CSS declarations

    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
     MUNDO
    -1.04
     siger
    -1.03
    ๗
    -1.00
    
    -0.97
    MouseListener
    -0.97
     conforman
    -0.97
     られ
    -0.96
     hjemmeside
    -0.93
     aéreo
    -0.93
    </strong>
    -0.92
    POSITIVE LOGITS
    Vlast
    1.08
     BECAUSE
    1.05
     населення
    1.04
    That
    1.02
    THAT
    1.02
    because
    0.96
    carnated
    0.95
    Aantal
    0.94
    äj
    0.94
    IDENTAL
    0.94
    Activations Density 0.034%

    No Known Activations