© 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. 21718
    Prev
    Next
    INDEX
    Explanations

    css html javascript xml selectors

    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
    櫚
    -2.53
    i
    -2.42
    but
    -2.34
    蹋
    -2.30
     But
    -2.30
    Sebelumnya
    -2.28
    Ketika
    -2.23
    Seperti
    -2.16
    Setiap
    -2.13
    s
    -2.13
    POSITIVE LOGITS
     porque
    2.81
    部分が
    2.64
     BECAUSE
    2.59
     perché
    2.45
    .’”
    2.36
    ྵ
    2.34
     utiliza
    2.34
     you
    2.31
    镚
    2.28
     salvaje
    2.23
    Activations Density 0.004%

    No Known Activations