© 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. 70395
    Prev
    Next
    INDEX
    Explanations

    update or patch

    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
     unveils
    -1.05
    helps
    -1.04
    liance
    -1.03
     ὑ
    -1.02
    Utilisation
    -1.02
    鸸
    -1.00
    création
    -1.00
     primeiro
    -0.99
    added
    -0.99
    瑗
    -0.98
    POSITIVE LOGITS
    update
    1.23
     their
    1.23
    just
    1.17
    修改
    1.06
     change
    1.02
     as
    1.02
     or
    1.00
     update
    1.00
     and
    0.99
     old
    0.99
    Activations Density 0.012%

    No Known Activations