© 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. 10-GEMMASCOPE-RES-131K
    7. 100791
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

    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
     and
    -2.67
     or
    -2.39
     with
    -2.11
     both
    -1.44
    してきました
    -1.41
    したので
    -1.36
     был
    -1.35
     three
    -1.35
     some
    -1.34
     give
    -1.33
    POSITIVE LOGITS
     REALLY
    1.51
    during
    1.39
     lmao
    1.38
    </strong>
    1.37
     atualmente
    1.35
     insanely
    1.34
     MICHAEL
    1.34
    ഀ
    1.32
     elegante
    1.28
     unn
    1.28
    Activations Density 0.149%

    No Known Activations