© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42818
    Prev
    Next
    INDEX
    Explanations

    code declaration and type String

    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
     например
    -1.23
    {*}
    -1.18
    например
    -1.18
    ties
    -1.17
     jembatan
    -1.16
    izadas
    -1.13
     некото
    -1.13
    }());
    -1.13
    ang
    -1.13
    зовать
    -1.13
    POSITIVE LOGITS
     when
    1.62
     its
    1.57
     that
    1.56
    bilisi
    1.27
     because
    1.24
    泽东
    1.24
     его
    1.23
     savu
    1.23
     and
    1.20
     herhangi
    1.19
    Activations Density 0.022%

    No Known Activations