© 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. 123976
    Prev
    Next
    INDEX
    Explanations

    extending through or from

    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
    4
    -2.38
    2
    -1.91
    6
    -1.89
    9
    -1.88
    0
    -1.83
    7
    -1.78
    5
    -1.75
    3
    -1.72
    也只是
    -1.72
     défauts
    -1.62
    POSITIVE LOGITS
     in
    2.28
     with
    1.69
     there
    1.46
    錚
    1.44
     know
    1.41
    三日
    1.38
     these
    1.38
    ⁈
    1.37
     connect
    1.34
     through
    1.29
    Activations Density 0.092%

    No Known Activations