© 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. 71045
    Prev
    Next
    INDEX
    Explanations

    testing functions

    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
    鹀
    -1.98
     kosme
    -1.77
    .-.
    -1.74
     potongan
    -1.73
     hectáreas
    -1.71
     kemasan
    -1.70
    猡
    -1.70
    ⇹
    -1.70
    ༵
    -1.70
     maleta
    -1.66
    POSITIVE LOGITS
     of
    2.00
    Thus
    1.62
     endast
    1.53
     definately
    1.52
     Commonly
    1.46
     hurl
    1.44
     They
    1.42
    essere
    1.39
     ambivalent
    1.37
     Subsequently
    1.36
    Activations Density 0.006%

    No Known Activations