© 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. 73627
    Prev
    Next
    INDEX
    Explanations

    format specifiers and code formatting

    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
     autres
    -1.73
     diversos
    -1.45
     alcune
    -1.41
    <bos>
    -1.41
     europé
    -1.36
     certamente
    -1.34
    aning
    -1.31
     LONDON
    -1.29
    糁
    -1.28
    discussed
    -1.27
    POSITIVE LOGITS
     from
    1.50
     supremely
    1.15
     %
    1.14
     on
    1.14
     superbly
    1.13
     during
    1.12
    飚
    1.11
     undeniably
    1.09
     exquisitely
    1.09
     +
    1.08
    Activations Density 0.010%

    No Known Activations