© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    code and special characters

    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
     that
    -1.55
     desmotiv
    -1.26
     it
    -1.23
    がなく
    -1.19
     those
    -1.14
    ！』
    -1.13
    があり
    -1.13
     predomin
    -1.12
    方針
    -1.10
    archical
    -1.09
    POSITIVE LOGITS
     sichere
    1.24
     reconocidos
    1.22
     -.
    1.22
     начинают
    1.21
     -
    1.20
    ところに
    1.20
     ПРЕ
    1.15
     capaces
    1.14
    不仅
    1.14
         
    1.14
    Activations Density 0.009%

    No Known Activations