© 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. 25890
    Prev
    Next
    INDEX
    Explanations

    graphics cards

    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
     "";
    -1.63
    沨
    -1.41
    
    -1.38
    ▾
    -1.32
    %">
    -1.31
     cucharadas
    -1.28
    ”
    -1.28
    "]["
    -1.28
    ."
    -1.25
     otros
    -1.23
    POSITIVE LOGITS
     obicei
    1.55
    Награды
    1.44
     针
    1.41
     orientação
    1.40
    哙
    1.30
    quilo
    1.29
     overzicht
    1.24
     reizen
    1.23
    quele
    1.21
     данным
    1.21
    Activations Density 0.032%

    No Known Activations