© 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. 19007
    Prev
    Next
    INDEX
    Explanations

    mistakes, errors, and glitches

    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
     is
    -1.46
     yourself
    -1.17
     fortæ
    -1.16
    ända
    -1.10
     junto
    -1.10
    Year
    -1.06
     információk
    -1.06
     incluso
    -1.05
    ᴍ
    -1.04
    IZACIÓN
    -1.03
    POSITIVE LOGITS
     between
    1.26
     or
    1.26
    サリー
    1.17
    rassed
    1.17
     baisse
    1.16
    アム
    1.15
     enkele
    1.14
    собенности
    1.14
     zwischen
    1.13
    なんでも
    1.12
    Activations Density 0.059%

    No Known Activations