© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72655
    Prev
    Next
    INDEX
    Explanations

    academic paper identifiers

    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
    );
    -1.98
     CELLS
    -1.96
    翾
    -1.93
    );
    -1.88
    韪
    -1.86
     évek
    -1.78
    ");
    -1.78
    ");
    -1.77
    💐
    -1.76
    इटम
    -1.74
    POSITIVE LOGITS
    4
    2.38
    3
    2.38
    2
    2.33
    6
    2.17
    0
    2.09
    s
    2.06
    5
    1.98
    7
    1.97
    8
    1.95
     Theore
    1.80
    Activations Density 0.013%

    No Known Activations