© 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. 10-GEMMASCOPE-RES-131K
    7. 129836
    Prev
    Next
    INDEX
    Explanations

    import statements with from

    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
    拶
    -1.68
     nossa
    -1.36
    鏷
    -1.31
    '].
    -1.26
     Однако
    -1.25
    ⡾
    -1.25
     così
    -1.24
     allerdings
    -1.23
     definiciones
    -1.23
     $
    -1.21
    POSITIVE LOGITS
     ucap
    1.73
     ungkap
    1.55
     ujar
    1.54
     tutur
    1.54
     melay
    1.50
     perak
    1.41
     kesel
    1.41
    4
    1.40
    with
    1.40
     cerdas
    1.38
    Activations Density 0.031%

    No Known Activations