© 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. 80799
    Prev
    Next
    INDEX
    Explanations

    file creation metadata

    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
     from
    -1.65
    ಭ
    -1.42
     when
    -1.38
     for
    -1.33
    Istanbul
    -1.27
     kérdés
    -1.25
     after
    -1.24
     fasse
    -1.23
     dezelfde
    -1.23
     hoppas
    -1.23
    POSITIVE LOGITS
    still
    1.57
    My
    1.44
    _
    1.41
     deines
    1.31
     my
    1.31
     recientemente
    1.30
     großes
    1.27
     некоторых
    1.24
    その
    1.23
    i
    1.23
    Activations Density 0.030%

    No Known Activations