© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102016
    Prev
    Next
    INDEX
    Explanations

    city, products, walks, sites

    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
     they
    -2.31
     that
    -1.96
     таких
    -1.73
     simplu
    -1.59
     there
    -1.58
    ׳
    -1.57
     Eſ
    -1.53
     învă
    -1.51
     Conſ
    -1.50
     complètement
    -1.45
    POSITIVE LOGITS
     with
    2.67
     or
    2.17
     first
    1.73
     your
    1.63
     additional
    1.60
     aurez
    1.52
     със
    1.45
     виправи
    1.42
     again
    1.42
     још
    1.41
    Activations Density 0.021%

    No Known Activations