© 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. 93213
    Prev
    Next
    INDEX
    Explanations

    Robert Wynne

    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
     of
    -1.49
    ！】
    -1.27
     plafond
    -1.25
     sirop
    -1.16
    ampang
    -1.16
     sirvió
    -1.16
     cordoba
    -1.15
    ಱ
    -1.14
     palermo
    -1.14
     対策
    -1.14
    POSITIVE LOGITS
    不时
    1.34
    ᴋ
    1.34
    Cartney
    1.20
    了下去
    1.17
    ॑
    1.17
     xxx
    1.16
     различ
    1.14
     estos
    1.12
     aquel
    1.11
    leness
    1.09
    Activations Density 0.000%

    No Known Activations