© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58408
    Prev
    Next
    INDEX
    Explanations

    coding constructs and imports

    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
     itself
    -1.77
     it
    -1.65
    はもちろん
    -1.33
    rewind
    -1.32
     to
    -1.22
    СЯ
    -1.21
     its
    -1.16
     certain
    -1.13
    なんですが
    -1.12
    ОВ
    -1.10
    POSITIVE LOGITS
     všechny
    1.60
    (!__
    1.40
     щодо
    1.37
     работать
    1.30
    )=\
    1.27
    }=\
    1.26
    これも
    1.26
    );
    1.26
     Chriftian
    1.24
     cependant
    1.23
    Activations Density 0.009%

    No Known Activations