© 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. 22434
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Однако
    -1.76
     Поэтому
    -1.49
     Таким
    -1.32
     Primarily
    -1.29
     ندارم
    -1.29
    푉
    -1.28
    iligung
    -1.25
     eigentlichen
    -1.25
    ittäin
    -1.23
    белый
    -1.23
    POSITIVE LOGITS
     воздух
    1.32
     you
    1.30
    ׳
    1.22
     they
    1.19
    тент
    1.18
    ierz
    1.18
    指甲
    1.16
    Which
    1.14
    dagen
    1.13
    Ď
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.