© 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. 19334
    Prev
    Next
    INDEX
    Explanations

    closing punctuation followed by name or quote

    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
    焢
    -2.36
    ኧ
    -2.33
    鉏
    -2.25
    くちゃ
    -2.23
    s
    -2.22
     VOUS
    -2.22
     Répondre
    -2.22
    "--
    -2.20
     thoſe
    -2.14
     Visita
    -2.14
    POSITIVE LOGITS
     to
    2.38
    to
    2.28
     чтобы
    2.23
     of
    2.16
     is
    2.09
    an
    2.08
    矢量
    2.06
    z
    2.00
     or
    2.00
    )
    1.93
    Activations Density 0.006%

    No Known Activations