© 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. 33923
    Prev
    Next
    INDEX
    Explanations

    named lakes

    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
     Roughly
    -2.39
     Selecting
    -2.33
    
    -2.28
    的很
    -2.22
    ↵
    -2.19
    玧
    -2.19
     glaring
    -2.16
     Hardly
    -2.09
     применяется
    -2.02
     bland
    -1.98
    POSITIVE LOGITS
    \
    2.88
     '-':
    2.30
     altre
    2.28
    )
    2.25
     eller
    2.22
     QtCore
    2.16
    ſam
    2.14
    ༛
    2.14
     noen
    2.11
     arah
    2.11
    Activations Density 0.010%

    No Known Activations