© 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. 28922
    Prev
    Next
    INDEX
    Explanations

    mixing together

    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
    :”
    -2.53
    ;”
    -2.16
    ’
    -2.14
     vollständige
    -2.03
    ”-
    -2.02
    ”、“
    -1.99
     nigdy
    -1.94
    ”;
    -1.94
    }}\
    -1.92
    ’”
    -1.90
    POSITIVE LOGITS
     \&
    2.31
    nocení
    2.08
    Kedua
    1.95
    uttgart
    1.91
     mélange
    1.90
    mixing
    1.85
    Mereka
    1.82
     dedans
    1.79
    Assessing
    1.75
    iding
    1.73
    Activations Density 0.045%

    No Known Activations