© 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. 12292
    Prev
    Next
    INDEX
    Explanations

    WASHINGTON DC

    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
    细腻
    -1.65
    Fungsi
    -1.53
    𖣘
    -1.48
     российской
    -1.46
     forthwith
    -1.46
     onsdag
    -1.45
     previos
    -1.45
    鮡
    -1.44
     fantastisk
    -1.43
     fredag
    -1.42
    POSITIVE LOGITS
     either
    1.71
     about
    1.69
     unless
    1.66
     is
    1.65
     also
    1.52
     have
    1.51
     which
    1.47
     until
    1.44
     used
    1.41
     because
    1.41
    Activations Density 0.002%

    No Known Activations