© 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. 10-GEMMASCOPE-RES-131K
    4. 19832
    Prev
    Next
    INDEX
    Explanations

    directory paths and __DIR__

    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_10/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
    The
    -3.23
    .......
    -2.86
    ....
    -2.84
    .....
    -2.72
    ......
    -2.59
    There
    -2.58
     große
    -2.58
     vollständige
    -2.52
    ........
    -2.52
     menschliche
    -2.48
    POSITIVE LOGITS
    a
    2.84
    别人的
    2.77
    也将
    2.69
    蔸
    2.66
    y
    2.63
    鼍
    2.59
    が多く
    2.53
    齮
    2.52
    archiwizowane
    2.50
    阏
    2.47
    Activations Density 0.004%

    No Known Activations