© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35500
    Prev
    Next
    INDEX
    Explanations

    press conference, hearing, meetings, debates

    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
    軀
    -1.09
     celebrates
    -1.02
    fa
    -1.02
     начали
    -1.00
     devotes
    -0.98
     sends
    -0.98
    means
    -0.96
     refers
    -0.94
    y
    -0.91
    z
    -0.91
    POSITIVE LOGITS
     nanti
    1.16
     where
    1.15
    historie
    1.11
     sereia
    1.10
     boneca
    1.09
    kabel
    1.05
    kapital
    1.05
    
    1.04
    legende
    1.01
    komfort
    1.01
    Activations Density 0.046%

    No Known Activations