© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105606
    Prev
    Next
    INDEX
    Explanations

    baseball walks and bases

    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
    1
    -1.65
     它
    -1.52
     każdy
    -1.48
     It
    -1.47
    也是
    -1.45
    出手
    -1.39
    在地上
    -1.38
     المعلومات
    -1.36
    4
    -1.34
    g
    -1.33
    POSITIVE LOGITS
    Abbiamo
    1.65
     OGSÅ
    1.57
     any
    1.52
    This
    1.50
    }];
    1.42
    thoscope
    1.42
    马逊
    1.41
     a
    1.39
    )))));
    1.37
    ardecer
    1.35
    Activations Density 0.007%

    No Known Activations