© 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. 84039
    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
    стоит
    -1.59
     "..\..\..\
    -1.57
    cherichia
    -1.54
    ">−
    -1.54
    таки
    -1.53
     "..\..\
    -1.48
    cketed
    -1.47
    失去了
    -1.45
    kiem
    -1.45
    ÓN
    -1.43
    POSITIVE LOGITS
     also
    1.59
    an
    1.55
    It
    1.52
    Also
    1.38
    He
    1.36
     the
    1.30
    了一個
    1.26
     this
    1.21
     other
    1.20
     kehamilan
    1.20
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.