© 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. 112412
    Prev
    Next
    INDEX
    Explanations

    list of items and concepts

    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
     it
    -1.59
     mantém
    -1.52
     แท
    -1.49
    '
    -1.49
     ation
    -1.46
     ทาง
    -1.45
     
    -1.45
     ☺️
    -1.45
     🥰
    -1.44
     antaranya
    -1.44
    POSITIVE LOGITS
     a
    2.20
    This
    1.57
    Vendredi
    1.52
     an
    1.51
    そして
    1.50
    嗒
    1.50
    悒
    1.45
     our
    1.43
     lipca
    1.43
    ၜ
    1.42
    Activations Density 0.098%

    No Known Activations