© 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. 38754
    Prev
    Next
    INDEX
    Explanations

    idiomatic phrases

    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
    ¡¡
    -1.59
     europé
    -1.38
    monger
    -1.35
    ющим
    -1.35
    ङ
    -1.28
    ё
    -1.27
    guys
    -1.26
    鹀
    -1.24
    dozer
    -1.24
    REB
    -1.23
    POSITIVE LOGITS
    enerys
    1.37
    ϶
    1.34
    分に
    1.22
     написал
    1.20
    5
    1.19
     blazing
    1.18
     worst
    1.17
    vers
    1.17
     staggering
    1.16
     Ähn
    1.16
    Activations Density 0.019%

    No Known Activations