© 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. 67475
    Prev
    Next
    INDEX
    Explanations

    question or colon

    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
     three
    -1.41
    厦
    -1.34
     two
    -1.32
    😂😂😂😂
    -1.30
     Bemerkungen
    -1.29
     both
    -1.20
     our
    -1.20
     I
    -1.20
     freilich
    -1.20
     June
    -1.18
    POSITIVE LOGITS
    おわりに
    1.55
    bảng
    1.52
     pittores
    1.52
     saco
    1.45
     ‌
    1.43
     enthousi
    1.43
    bước
    1.42
     velours
    1.41
    phòng
    1.39
     épis
    1.38
    Activations Density 0.000%

    No Known Activations