© 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. 12053
    Prev
    Next
    INDEX
    Explanations

    specific compound phrases

    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
    er
    -3.50
    and
    -3.25
    to
    -3.22
    in
    -2.89
    O
    -2.88
    it
    -2.59
    Y
    -2.34
     he
    -2.28
     To
    -2.28
    as
    -2.27
    POSITIVE LOGITS
    lossians
    2.59
    ꯸
    2.48
    摭
    2.47
    ᐕ
    2.45
    蜮
    2.36
     beinahe
    2.36
    僦
    2.31
    recette
    2.30
    鯪
    2.28
     入っ
    2.22
    Activations Density 0.030%

    No Known Activations