© 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. 128164
    Prev
    Next
    INDEX
    Explanations

    different or multiple instances

    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
     that
    -1.99
     to
    -1.55
    你是不是
    -1.38
    ers
    -1.31
     either
    -1.28
     Either
    -1.24
    to
    -1.23
     out
    -1.23
    Either
    -1.20
     until
    -1.20
    POSITIVE LOGITS
    icidio
    1.39
     comenzar
    1.38
    ってました
    1.34
     Gebir
    1.33
    leggio
    1.32
    larla
    1.32
     oreja
    1.30
    ܿ
    1.27
     какие
    1.27
     Kullan
    1.27
    Activations Density 0.240%

    No Known Activations