© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1852
    Prev
    Next
    INDEX
    Explanations

    Let $A$ and $B$

    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
     diinginkan
    -1.50
     there
    -1.43
     illustre
    -1.39
     telo
    -1.36
    ゚)
    -1.35
    殯
    -1.34
     重
    -1.31
     devia
    -1.30
    if
    -1.30
    unno
    -1.30
    POSITIVE LOGITS
     can
    1.95
     cuando
    1.77
     when
    1.70
     that
    1.67
    で
    1.52
    ),
    1.51
     and
    1.50
     are
    1.42
    catálogo
    1.38
     whose
    1.37
    Activations Density 0.029%

    No Known Activations