© 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. 112568
    Prev
    Next
    INDEX
    Explanations

    Windows UI and apps

    np_acts-logits-general · gemini-2.5-flash-lite

    Windows API and UWP (Universal Windows Platform) code and documentation elements.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     unserem
    -1.50
    。"
    -1.34
     vitesses
    -1.34
     diventa
    -1.30
    万美元
    -1.28
     juiste
    -1.27
     brengt
    -1.27
    ンスター
    -1.23
     pasture
    -1.22
     vestidos
    -1.21
    POSITIVE LOGITS
     =
    1.28
    ??????
    1.26
    rippa
    1.24
    %
    1.23
     promesse
    1.20
     confidentialité
    1.15
    lllll
    1.15
     xb
    1.14
    [%
    1.13
     Cruiser
    1.11
    Activations Density 0.069%

    No Known Activations