© 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. 34-GEMMASCOPE-RES-131K
    7. 2308
    Prev
    Next
    INDEX
    Explanations

    numbers starting with 6

    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_34/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
     there
    -1.52
     still
    -1.01
     terribly
    -0.92
     necessary
    -0.91
     had
    -0.88
    这个世界
    -0.84
    There
    -0.84
     essential
    -0.83
     although
    -0.82
     desperately
    -0.82
    POSITIVE LOGITS
    paigns
    1.07
     feas
    0.98
    杷
    0.92
    再次
    0.91
    穽
    0.91
     Dien
    0.88
    otent
    0.88
    ꜥ
    0.87
    닙
    0.86
    manie
    0.85
    Activations Density 0.022%

    No Known Activations