© 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. 75384
    Prev
    Next
    INDEX
    Explanations

    code increments/decrements

    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
    -1.87
     &
    -1.77
    ⁛
    -1.59
     is
    -1.54
    gives
    -1.48
    諼
    -1.47
     amd
    -1.44
    搋
    -1.38
     renowned
    -1.38
    doesn
    -1.37
    POSITIVE LOGITS
    Ᏺ
    2.02
     egenskaper
    1.74
     pelindung
    1.73
    ioni
    1.67
     These
    1.67
    Tetapi
    1.63
    —¡
    1.63
     flesta
    1.61
     ヶ
    1.59
     különböz
    1.59
    Activations Density 0.001%

    No Known Activations