© 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. 110875
    Prev
    Next
    INDEX
    Explanations

    MessageBox, ToolTip, file path

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "toast" or "Toast" in various contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     Aufl
    -2.41
     That
    -2.39
    ?"
    -2.13
     و
    -2.05
     Our
    -2.03
     Mereka
    -1.99
     Would
    -1.98
     würden
    -1.98
    AutoresizingMask
    -1.97
     WHAT
    -1.93
    POSITIVE LOGITS
    ,
    2.13
    亖
    2.09
     that
    2.09
    sandalia
    2.02
     墊
    1.95
    寕
    1.88
    仮想
    1.80
    wakili
    1.77
    你这
    1.76
    ㉕
    1.76
    Activations Density 0.000%

    No Known Activations