© 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. 74884
    Prev
    Next
    INDEX
    Explanations

    place to do things

    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
    狨
    -1.58
    さまざまな
    -1.58
     rústico
    -1.50
    ጁ
    -1.50
    向けの
    -1.42
     japones
    -1.42
    こちら
    -1.42
    䛗
    -1.41
     motocicletas
    -1.41
     schien
    -1.40
    POSITIVE LOGITS
     from
    2.17
     for
    2.16
     which
    2.02
     that
    1.54
     to
    1.42
     including
    1.40
     with
    1.38
    ,”
    1.36
    ’,
    1.32
     has
    1.30
    Activations Density 0.023%

    No Known Activations