© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59910
    Prev
    Next
    INDEX
    Explanations

    bridging headers and CF types

    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
     muy
    -1.09
    naires
    -1.07
     as
    -1.07
     intptr
    -1.06
    子は
    -1.04
     [
    -1.02
     czyli
    -1.02
     will
    -1.01
     with
    -1.00
     paar
    -1.00
    POSITIVE LOGITS
     triunfo
    1.36
     eases
    1.32
    Produits
    1.27
    Allows
    1.27
     disple
    1.25
     準備
    1.25
    Entrée
    1.22
     trámite
    1.22
    SetState
    1.21
     Können
    1.21
    Activations Density 0.074%

    No Known Activations