© 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. 19337
    Prev
    Next
    INDEX
    Explanations

    `viewDidLoad` code blocks

    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
    There
    -2.89
     burbu
    -2.59
    Although
    -2.56
    鵟
    -2.39
    ╿
    -2.39
    觧
    -2.38
     successivo
    -2.31
    ଢ
    -2.31
    their
    -2.31
    when
    -2.31
    POSITIVE LOGITS
    '
    3.28
    ↵↵
    2.41
    )$
    2.33
    ’
    2.25
     là
    2.17
     \
    2.06
     $
    2.05
    in
    2.05
    などは
    2.05
     takže
    2.03
    Activations Density 0.002%

    No Known Activations