© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123884
    Prev
    Next
    INDEX
    Explanations

    of the

    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
     suffisamment
    -1.91
    But
    -1.59
    out
    -1.52
    чках
    -1.51
    хівовано
    -1.47
    There
    -1.47
     становятся
    -1.47
    You
    -1.41
    Your
    -1.41
    Ask
    -1.40
    POSITIVE LOGITS
     with
    1.86
     has
    1.78
     as
    1.77
     from
    1.71
     the
    1.65
     his
    1.53
     its
    1.52
    他对
    1.47
     needed
    1.47
     what
    1.47
    Activations Density 0.041%

    No Known Activations