© 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. 42561
    Prev
    Next
    INDEX
    Explanations

    message and kind declarations

    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
    댔
    -1.65
     mauva
    -1.59
     áng
    -1.59
     zoude
    -1.53
    訁
    -1.52
    Schule
    -1.52
    厹
    -1.48
    鲞
    -1.45
    espół
    -1.42
    糁
    -1.39
    POSITIVE LOGITS
     that
    1.55
     for
    1.52
     to
    1.49
    We
    1.38
     our
    1.37
     Since
    1.35
     where
    1.35
     of
    1.31
     such
    1.27
    In
    1.24
    Activations Density 0.006%

    No Known Activations