© 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. 34-GEMMASCOPE-RES-131K
    4. 117882
    Prev
    Next
    INDEX
    Explanations

    code comments and structures

    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
    鄴
    -0.85
    ochim
    -0.84
    maxn
    -0.84
     perv
    -0.83
     españolas
    -0.83
    lillah
    -0.83
    vegetarian
    -0.79
    dropping
    -0.78
    Jangan
    -0.77
     légiti
    -0.77
    POSITIVE LOGITS
     against
    0.93
    こな
    0.78
     району
    0.76
    自然
    0.74
    BR
    0.73
    olar
    0.71
    lic
    0.71
    ปร
    0.71
    析
    0.71
    ese
    0.70
    Activations Density 0.013%

    No Known Activations