© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19266
    Prev
    Next
    INDEX
    Explanations

    check the or your

    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
     to
    -2.45
     They
    -1.97
     Could
    -1.96
     Why
    -1.95
     be
    -1.91
    )$,
    -1.88
    </h3>
    -1.87
     That
    -1.86
     Whether
    -1.84
     of
    -1.81
    POSITIVE LOGITS
    Ꮠ
    2.36
     мои
    1.85
    кроссовки
    1.85
    Makanan
    1.84
    girls
    1.80
    嗞
    1.80
    𞤮
    1.79
     Medan
    1.79
    вгений
    1.77
     Kere
    1.74
    Activations Density 0.009%

    No Known Activations