© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130296
    Prev
    Next
    INDEX
    Explanations

    software release versions and builds

    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
     when
    -1.26
    after
    -1.17
    定制
    -1.13
     когда
    -1.10
     so
    -1.09
     окружающей
    -1.08
     ayudar
    -1.05
    當
    -1.05
     quando
    -1.04
     ideas
    -1.02
    POSITIVE LOGITS
     release
    1.55
     MAYOR
    1.47
     PLATES
    1.45
     MUSEUM
    1.42
     OBIT
    1.42
     INDUSTRIES
    1.41
     INDUSTR
    1.39
     changelog
    1.39
     KITCHEN
    1.39
     pantalon
    1.38
    Activations Density 0.082%

    No Known Activations