© 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. 66939
    Prev
    Next
    INDEX
    Explanations

    names, labels, or list items

    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
    Those
    -1.48
     fotógrafo
    -1.41
    Some
    -1.41
     jurado
    -1.38
    Just
    -1.38
     mencer
    -1.33
     organizador
    -1.30
    You
    -1.30
     eventuell
    -1.29
     those
    -1.28
    POSITIVE LOGITS
    </h2>
    1.76
     heu
    1.58
     biografi
    1.48
     zei
    1.47
     citroen
    1.44
     stadion
    1.44
     tev
    1.38
     idi
    1.34
     damen
    1.30
     eene
    1.28
    Activations Density 0.028%

    No Known Activations