© 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. 22038
    Prev
    Next
    INDEX
    Explanations

    resounding yes or MEH

    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
     only
    -1.55
     it
    -1.42
     people
    -1.30
     these
    -1.24
    ICED
    -1.23
    同时也
    -1.22
     maler
    -1.21
    UNTIME
    -1.20
    پز
    -1.18
     jamur
    -1.17
    POSITIVE LOGITS
    gencias
    1.60
     '
    1.55
    或
    1.46
    neling
    1.45
     „
    1.45
    "]="
    1.39
     např
    1.37
     nejlepší
    1.37
     either
    1.34
    ","
    1.29
    Activations Density 0.067%

    No Known Activations