© 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. 118019
    Prev
    Next
    INDEX
    Explanations

    numbers and quantity ranges

    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
     PROBLE
    -0.98
    świę
    -0.96
    żna
    -0.93
    ркут
    -0.92
     aumentare
    -0.91
    erschied
    -0.89
    ▸
    -0.89
    ClassPath
    -0.88
    wój
    -0.88
    >>>>>>>
    -0.88
    POSITIVE LOGITS
     or
    4.13
    以上
    2.30
    以上的
    1.95
    以上の
    1.71
     이상
    1.70
    以下
    1.62
     and
    1.46
    或
    1.41
     или
    1.38
     Or
    1.35
    Activations Density 0.115%

    No Known Activations