© 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. 111008
    Prev
    Next
    INDEX
    Explanations

    making predictions or statements

    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
    tabilis
    -0.96
     handel
    -0.93
    んだん
    -0.93
     بیان
    -0.92
     Finds
    -0.91
     확인함
    -0.91
    })}\
    -0.91
    shown
    -0.90
    bereiche
    -0.90
     verbatim
    -0.89
    POSITIVE LOGITS
    在你
    0.94
    nappropriate
    0.94
    piller
    0.91
    赝
    0.85
    Ար
    0.84
    diğinde
    0.84
    Now
    0.82
     cuando
    0.80
     gewiß
    0.80
     quæ
    0.79
    Activations Density 0.059%

    No Known Activations