© 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. 84826
    Prev
    Next
    INDEX
    Explanations

    dependent on

    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
    </i>
    -1.98
    ."
    -1.75
    剜
    -1.54
     considérons
    -1.52
    闼
    -1.50
     נוספת
    -1.45
    abestanden
    -1.44
    鹉
    -1.43
    脸上的
    -1.43
    intios
    -1.43
    POSITIVE LOGITS
     for
    2.00
    {
    1.82
     on
    1.78
     Untuk
    1.67
    ización
    1.61
     by
    1.54
     such
    1.53
    それを
    1.52
    ↵↵
    1.51
    必须
    1.51
    Activations Density 0.018%

    No Known Activations