© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13056
    Prev
    Next
    INDEX
    Explanations

    structured data and identifiers

    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
     questionSearch
    -2.39
    موقع
    -2.25
     火鍋
    -2.13
    焢
    -2.11
     augus
    -2.11
     saveiro
    -2.09
     福袋
    -2.08
     camiset
    -2.08
     abiye
    -2.05
    <bos>
    -2.02
    POSITIVE LOGITS
     to
    3.16
     '
    2.45
     ...
    2.31
     has
    2.11
     -
    2.11
     it
    2.09
     At
    2.05
     a
    2.00
    )))),
    1.99
     ('
    1.98
    Activations Density 0.020%

    No Known Activations