© 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. 38165
    Prev
    Next
    INDEX
    Explanations

    East Antrim publications

    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
     oxidase
    -0.85
     Freiburg
    -0.77
    onesome
    -0.76
    的食物
    -0.73
    aryng
    -0.72
    ång
    -0.71
    jourd
    -0.71
     Catholic
    -0.71
    Earth
    -0.70
    ímp
    -0.69
    POSITIVE LOGITS
     hexagonal
    0.75
    isław
    0.74
    ंडल
    0.71
    rdata
    0.71
     dungeons
    0.70
    estors
    0.69
     Ahu
    0.69
    🧥
    0.68
     parm
    0.68
     Giz
    0.67
    Activations Density 0.015%

    No Known Activations