© 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. 22-GEMMASCOPE-RES-131K
    7. 75157
    Prev
    Next
    INDEX
    Explanations

    code and math problems

    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_22/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
     to
    -1.50
     for
    -1.39
     also
    -1.38
     leksikon
    -1.26
     most
    -1.26
     other
    -1.24
     even
    -1.23
     by
    -1.16
    饅
    -1.12
    餞
    -1.12
    POSITIVE LOGITS
     manteiga
    1.30
     voordelen
    1.29
    明日は
    1.19
    為に
    1.17
     proberen
    1.16
    きち
    1.16
     wensen
    1.14
    もうすぐ
    1.13
     resultaten
    1.12
    側から
    1.12
    Activations Density 0.003%

    No Known Activations