© 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. 19140
    Prev
    Next
    INDEX
    Explanations

    software licenses and usage exceptions

    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
     when
    -1.80
     ketika
    -1.77
    cích
    -1.68
     the
    -1.59
     kolejny
    -1.57
    When
    -1.51
    quando
    -1.45
    cuando
    -1.45
     quando
    -1.44
    ਆਂ
    -1.39
    POSITIVE LOGITS
     to
    1.84
    -
    1.71
     -
    1.61
     by
    1.59
     (
    1.55
    ,
    1.55
     at
    1.46
     for
    1.46
     of
    1.45
    ではなく
    1.36
    Activations Density 0.245%

    No Known Activations