© 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. 48533
    Prev
    Next
    INDEX
    Explanations

    field of the invention

    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
     from
    -1.64
     if
    -1.48
    which
    -1.46
     for
    -1.42
    :
    -1.41
    (
    -1.37
     through
    -1.31
    M
    -1.31
    from
    -1.31
     userDao
    -1.30
    POSITIVE LOGITS
    这些
    1.62
    ↵
    1.41
    titial
    1.40
    這些
    1.36
     décé
    1.34
    eſ
    1.31
    Alemania
    1.30
    数据
    1.26
     célébr
    1.26
     ۸
    1.25
    Activations Density 0.028%

    No Known Activations