© 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. 22-GEMMASCOPE-RES-131K
    7. 15561
    Prev
    Next
    INDEX
    Explanations

    code syntax, mathematical formulas, or foreign words

    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_22/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
    Leírás
    -1.40
     corrobor
    -1.32
    餃
    -1.31
     in
    -1.24
    RAINE
    -1.24
    дні
    -1.23
    1
    -1.18
     mentales
    -1.16
     maroc
    -1.16
    CHOOL
    -1.16
    POSITIVE LOGITS
    nachweise
    1.41
    為に
    1.40
    conceito
    1.29
     niebla
    1.24
     Wochenende
    1.24
     associated
    1.23
     herramientas
    1.23
    のですか
    1.20
     emisiones
    1.19
     tracción
    1.18
    Activations Density 0.001%

    No Known Activations