© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41677
    Prev
    Next
    INDEX
    Explanations

    distances and locations

    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
     Antwerpen
    -1.38
    Ế
    -1.29
     MASSACHUSETTS
    -1.28
    ----------
    -1.27
     antena
    -1.27
    </u>
    -1.27
     attent
    -1.27
    PointerException
    -1.25
     "*",
    -1.24
     ARCHITECT
    -1.23
    POSITIVE LOGITS
     in
    1.99
     by
    1.89
     on
    1.76
     there
    1.62
     to
    1.55
     from
    1.54
     some
    1.48
     so
    1.47
     still
    1.38
     first
    1.35
    Activations Density 0.040%

    No Known Activations