© 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. 42047
    Prev
    Next
    INDEX
    Explanations

    program structure entities

    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
     more
    -1.82
     from
    -1.78
     our
    -1.77
     with
    -1.75
     that
    -1.64
     bringing
    -1.57
     creating
    -1.49
     giving
    -1.48
     and
    -1.44
     one
    -1.44
    POSITIVE LOGITS
     gena
    1.55
    despite
    1.49
    currently
    1.38
    last
    1.37
    就连
    1.34
    usually
    1.30
    fy
    1.30
    ining
    1.29
     assurent
    1.28
     utilisent
    1.28
    Activations Density 0.224%

    No Known Activations