© 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. 87149
    Prev
    Next
    INDEX
    Explanations

    closing code delimiters

    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
     your
    -1.57
     our
    -1.44
    がありますが
    -1.30
    denn
    -1.28
     нашем
    -1.27
     verrou
    -1.23
    姈
    -1.22
     encantador
    -1.22
     unsere
    -1.21
     élégante
    -1.21
    POSITIVE LOGITS
     from
    1.30
     is
    1.27
    LayoutPanel
    1.23
    точно
    1.18
     The
    1.13
     zarówno
    1.13
    似乎
    1.12
    Both
    1.12
    se
    1.10
    of
    1.09
    Activations Density 0.013%

    No Known Activations