© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8927
    Prev
    Next
    INDEX
    Explanations

    other than

    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
    ᷇
    -1.77
     наших
    -1.70
     нашим
    -1.64
    嗞
    -1.61
     nawet
    -1.55
    дцать
    -1.48
    Decide
    -1.47
     PUSTAKA
    -1.46
     แต่
    -1.45
    brtc
    -1.42
    POSITIVE LOGITS
     a
    2.28
     including
    1.80
     an
    1.66
     their
    1.60
     from
    1.48
     głównie
    1.44
    是
    1.43
    的是
    1.42
     this
    1.39
    dė
    1.38
    Activations Density 0.012%

    No Known Activations