© 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. 34-GEMMASCOPE-RES-131K
    7. 2771
    Prev
    Next
    INDEX
    Explanations

    1024

    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_34/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
    шин
    -0.77
    Provision
    -0.73
    mui
    -0.73
    八十
    -0.71
     Jong
    -0.71
    Prepared
    -0.71
    حياته
    -0.70
    туга
    -0.69
     dispositions
    -0.69
    MINIMUM
    -0.69
    POSITIVE LOGITS
    splitContainer
    0.77
    那麼
    0.76
     privacidade
    0.75
    𝑍
    0.74
    oderm
    0.74
     haupts
    0.73
     Siberia
    0.73
     duration
    0.73
    atical
    0.72
    inees
    0.71
    Activations Density 0.014%

    No Known Activations