© 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. 10-GEMMASCOPE-RES-131K
    7. 85583
    Prev
    Next
    INDEX
    Explanations

    wizard actions

    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_10/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
    </em>
    -2.41
    ᳝
    -2.38
    ases
    -2.33
    
    -2.27
     harika
    -2.25
    ↵
    -2.17
    ᯅ
    -2.16
     ComVisible
    -2.16
     czym
    -2.14
    禟
    -2.13
    POSITIVE LOGITS
     начинают
    3.11
     становятся
    2.83
    What
    2.75
     Any
    2.52
    <i>
    2.50
    the
    2.48
     الاجتماعي
    2.47
    皷
    2.45
     Hoping
    2.34
     Primarily
    2.33
    Activations Density 0.003%

    No Known Activations