© 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. 131029
    Prev
    Next
    INDEX
    Explanations

    Swift, Kotlin, Java, C++ code declarations

    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
     Chré
    -1.16
     november
    -1.16
     september
    -1.13
    
    -1.13
     kalau
    -1.13
     ちゃん
    -1.12
     december
    -1.12
    owieck
    -1.10
     (!
    -1.09
     если
    -1.09
    POSITIVE LOGITS
     from
    1.73
     it
    1.57
     with
    1.35
     could
    1.33
     while
    1.31
    4
    1.31
     först
    1.27
     can
    1.27
     would
    1.27
     хоче
    1.25
    Activations Density 0.016%

    No Known Activations