© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98751
    Prev
    Next
    INDEX
    Explanations

    sleep, dependencies, lie, seasonal, winter, protect, villains, slow, older

    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
    Negative Logits
     of
    -1.67
     as
    -1.43
    "><!--
    -1.42
     from
    -1.34
    ཿ
    -1.30
    [>
    -1.29
    "=>
    -1.28
    ">
    -1.28
    }]
    -1.28
    erde
    -1.27
    POSITIVE LOGITS
    价比
    1.42
    intéress
    1.29
    無駄
    1.29
     raffredd
    1.27
     membri
    1.27
     seulement
    1.26
     alimentare
    1.24
    を行いました
    1.22
    espé
    1.20
    を行います
    1.20
    Activations Density 0.598%

    No Known Activations