© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13574
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers like 12th

    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_10/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
    ﱠ
    -2.22
    廡
    -2.20
    啭
    -2.16
     riusc
    -2.14
    ⸒
    -2.11
     wiederhol
    -2.00
     gestartet
    -1.98
     flourishing
    -1.98
     pilotes
    -1.95
    岨
    -1.95
    POSITIVE LOGITS
    I
    2.39
    th
    2.20
    \
    2.05
    ."
    1.88
    man
    1.88
    it
    1.77
     Disabilities
    1.65
     こ
    1.59
    ","
    1.59
    by
    1.55
    Activations Density 0.083%

    No Known Activations