© 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. 556
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ところに
    -1.41
     and
    -1.41
     you
    -1.34
    おそ
    -1.23
    感じで
    -1.21
     the
    -1.13
     OGSÅ
    -1.13
    つづく
    -1.12
    ख़
    -1.11
    マジで
    -1.10
    POSITIVE LOGITS
    數
    1.26
    力
    1.24
     tristes
    1.22
    兩
    1.22
    ❉
    1.21
    度
    1.20
    立
    1.17
    流
    1.16
    ׇ
    1.13
    IQUES
    1.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.