© 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. 47876
    Prev
    Next
    INDEX
    Explanations

    named entities

    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
    ጵ
    -1.42
     collega
    -1.42
     первую
    -1.36
     évent
    -1.31
    没人
    -1.31
     bave
    -1.30
     kanker
    -1.29
    ⡰
    -1.28
    audiovisuel
    -1.27
     láser
    -1.27
    POSITIVE LOGITS
     as
    2.28
     by
    2.17
     from
    1.95
     but
    1.85
     after
    1.64
     at
    1.52
     with
    1.51
    The
    1.50
     so
    1.48
     through
    1.43
    Activations Density 0.098%

    No Known Activations