© 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. 10-GEMMASCOPE-RES-131K
    7. 69040
    Prev
    Next
    INDEX
    Explanations

    but, however, yet, although

    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
     will
    -1.72
     part
    -1.18
    岂
    -1.15
     offensichtlich
    -1.12
    rindo
    -1.10
    ｹ
    -1.09
     why
    -1.08
    buatan
    -1.08
     have
    -1.07
     Clothing
    -1.07
    POSITIVE LOGITS
    ния
    1.25
    idad
    1.24
    v
    1.23
    。「
    1.20
     assurent
    1.17
    。“
    1.16
    “……
    1.16
     ungefär
    1.16
     forder
    1.16
    といいます
    1.15
    Activations Density 0.327%

    No Known Activations