© 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. 73355
    Prev
    Next
    INDEX
    Explanations

    file system operations

    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
    蟊
    -1.46
    هاي
    -1.39
     Aggi
    -1.38
    犼
    -1.33
    
    -1.32
    戋
    -1.31
    tached
    -1.29
    歺
    -1.29
    
    -1.27
    鲥
    -1.27
    POSITIVE LOGITS
     a
    1.49
     both
    1.44
     any
    1.41
    _
    1.36
    !
    1.34
     giving
    1.32
     in
    1.32
    <bos>
    1.30
     Professional
    1.29
     not
    1.28
    Activations Density 0.156%

    No Known Activations