© 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. 34-GEMMASCOPE-RES-131K
    7. 47793
    Prev
    Next
    INDEX
    Explanations

    food dish compositions

    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_34/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
     dispositifs
    -1.36
     eenig
    -1.21
     boî
    -1.18
     sentiers
    -1.13
     くん
    -1.13
     câbles
    -1.10
     hemd
    -1.09
     visse
    -1.09
     constituer
    -1.09
     punkt
    -1.07
    POSITIVE LOGITS
     with
    1.38
     using
    1.32
     by
    1.28
     for
    1.16
     from
    1.13
     in
    1.05
     over
    1.02
     without
    1.00
     four
    0.94
     on
    0.94
    Activations Density 0.016%

    No Known Activations