© 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. 65533
    Prev
    Next
    INDEX
    Explanations

    combining lists or concepts

    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
     within
    -1.26
     at
    -1.23
     on
    -1.15
     any
    -1.07
     focused
    -1.02
     for
    -1.00
     ask
    -0.98
     about
    -0.98
     during
    -0.96
     through
    -0.93
    POSITIVE LOGITS
     both
    1.87
     både
    1.84
    both
    1.83
    BOTH
    1.62
    Both
    1.61
     दोनों
    1.61
     beide
    1.55
     BOTH
    1.54
     zarówno
    1.48
     beiden
    1.44
    Activations Density 0.025%

    No Known Activations