© 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. 86763
    Prev
    Next
    INDEX
    Explanations

    code function 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
     will
    -1.94
    na
    -1.73
    很多
    -1.72
    大部分
    -1.66
    許多
    -1.66
    这
    -1.64
    许多
    -1.64
    won
    -1.55
     ovviamente
    -1.55
     meeste
    -1.54
    POSITIVE LOGITS
     with
    2.38
     from
    2.00
     through
    1.68
    されていない
    1.67
     new
    1.66
     that
    1.66
     their
    1.63
     like
    1.54
    選んだ
    1.52
     this
    1.50
    Activations Density 0.018%

    No Known Activations