© 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. 71337
    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
     durante
    -1.42
     preponder
    -1.41
     dilapidated
    -1.37
     Portug
    -1.25
     kiedy
    -1.24
    <<<<<<<
    -1.20
     devast
    -1.18
     lorsque
    -1.17
     [.
    -1.16
     tässä
    -1.16
    POSITIVE LOGITS
     continues
    1.58
     brugt
    1.38
     gets
    1.36
     have
    1.34
     keeps
    1.33
     creates
    1.31
     puts
    1.30
     first
    1.24
     using
    1.23
     represents
    1.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.