© 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. 7788
    Prev
    Next
    INDEX
    Explanations

    names and specialized terms

    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
     nadru
    -1.53
     plenamente
    -1.49
     kabát
    -1.43
    珵
    -1.43
     conscientes
    -1.40
     geef
    -1.32
     chrétienne
    -1.31
    irregular
    -1.30
    assorted
    -1.28
    smiling
    -1.27
    POSITIVE LOGITS
    there
    1.74
     there
    1.53
    There
    1.48
     of
    1.37
     facie
    1.34
    Also
    1.29
    是一個
    1.23
    Também
    1.23
     There
    1.23
     Comuni
    1.20
    Activations Density 0.894%

    No Known Activations