© 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. 36448
    Prev
    Next
    INDEX
    Explanations

    code and math 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_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
     by
    -2.16
     if
    -1.46
     gave
    -1.37
     before
    -1.37
     during
    -1.35
     from
    -1.34
     took
    -1.31
     sejarah
    -1.27
     senhora
    -1.26
     ensures
    -1.25
    POSITIVE LOGITS
     automóviles
    1.52
     fantastic
    1.44
    沒
    1.42
     decidedly
    1.40
    described
    1.35
    Personally
    1.35
     zwi
    1.34
     trám
    1.34
     powodu
    1.34
    creating
    1.34
    Activations Density 0.001%

    No Known Activations