© 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. 10194
    Prev
    Next
    INDEX
    Explanations

    programming and tech news

    np_acts-logits-general · gemini-2.5-flash-lite

    references to Elon Musk and his companies (SpaceX, Neuralink, Starlink).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     For
    -2.44
    I
    -2.08
    !!!
    -1.98
    翃
    -1.94
    apatilla
    -1.93
     flurry
    -1.91
     Roughly
    -1.91
     ;
    -1.91
    ons
    -1.90
    ’
    -1.90
    POSITIVE LOGITS
    栊
    1.98
     bleus
    1.97
    现在的
    1.97
     bateaux
    1.96
     sains
    1.93
     inox
    1.93
    〡
    1.93
    饜
    1.91
     trous
    1.88
    felf
    1.87
    Activations Density 0.001%

    No Known Activations