© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40503
    Prev
    Next
    INDEX
    Explanations

    keys in data structures

    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
     siè
    -2.16
     Dinas
    -1.91
     favoriser
    -1.90
    į
    -1.88
     rigue
    -1.88
     faciliter
    -1.83
     empêcher
    -1.80
    particularly
    -1.80
     semblent
    -1.80
    meld
    -1.79
    POSITIVE LOGITS
     using
    2.72
     used
    2.41
     just
    2.41
     took
    2.38
     more
    2.33
     has
    2.22
     received
    2.22
     created
    2.20
     this
    2.19
     at
    2.17
    Activations Density 0.037%

    No Known Activations