© 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. 54175
    Prev
    Next
    INDEX
    Explanations

    Benin, Q:, As distracted, The intake

    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
     their
    -1.51
     all
    -1.48
     only
    -1.42
     our
    -1.33
     you
    -1.27
     both
    -1.26
     just
    -1.26
     two
    -1.20
     like
    -1.16
     first
    -1.15
    POSITIVE LOGITS
     DIFFERENT
    1.27
     不锈钢
    1.26
     salmón
    1.23
    Irlande
    1.20
     メンテナンス
    1.20
     Dinas
    1.18
     voed
    1.16
    Deel
    1.16
    estroy
    1.15
    different
    1.13
    Activations Density 0.000%

    No Known Activations