© 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. 47981
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
     Receiving
    -1.44
     Those
    -1.43
     those
    -1.38
     While
    -1.30
    暑假
    -1.30
     Today
    -1.27
    最近
    -1.27
    先日
    -1.26
     what
    -1.25
     slight
    -1.25
    POSITIVE LOGITS
     защото
    1.48
    𝟚
    1.31
     utilizadas
    1.24
    让他
    1.23
    让我
    1.23
    over
    1.23
     моего
    1.23
     罐
    1.20
     meinem
    1.17
    aS
    1.17
    Activations Density 0.009%

    No Known Activations