© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13779
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
     one
    -1.52
     possibly
    -1.20
     may
    -1.20
     its
    -1.19
     -
    -1.15
     to
    -1.15
     Once
    -1.14
    「
    -1.13
     One
    -1.13
     keep
    -1.13
    POSITIVE LOGITS
    当场
    1.33
     dekoratif
    1.28
     participer
    1.28
     productividad
    1.26
    涑
    1.25
     yelek
    1.24
     เครื่อง
    1.20
     取り付け
    1.19
     物語
    1.18
     senin
    1.18
    Activations Density 0.014%

    No Known Activations