© 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. 66884
    Prev
    Next
    INDEX
    Explanations

    Windows Forms applications

    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
     nœ
    -1.66
    alers
    -1.56
     fonde
    -1.54
     elegante
    -1.54
     intelligente
    -1.53
     cristales
    -1.52
     faune
    -1.51
     disques
    -1.51
    orto
    -1.48
     compagnon
    -1.48
    POSITIVE LOGITS
     but
    2.25
     to
    2.16
     on
    2.06
     this
    2.05
     and
    1.95
     since
    1.79
     We
    1.55
    0
    1.47
     with
    1.41
     цього
    1.39
    Activations Density 0.004%

    No Known Activations