© 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. 34791
    Prev
    Next
    INDEX
    Explanations

    API endpoints and paths

    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
     magnific
    -1.47
    acknowled
    -1.41
     incredi
    -1.38
     accessori
    -1.35
    primarily
    -1.34
    despite
    -1.30
     GETTING
    -1.29
     GRAND
    -1.28
    1
    -1.23
     dando
    -1.23
    POSITIVE LOGITS
     seems
    1.46
     seemed
    1.40
     at
    1.31
     using
    1.30
     started
    1.27
     without
    1.27
     their
    1.27
     unusually
    1.24
     Seems
    1.23
     makes
    1.22
    Activations Density 0.014%

    No Known Activations