© 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. 10-GEMMASCOPE-RES-131K
    7. 68816
    Prev
    Next
    INDEX
    Explanations

    bus

    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
    轵
    -3.17
     ſtate
    -3.14
    摃
    -3.02
    Ꮴ
    -2.98
    艄
    -2.95
    胪
    -2.94
    遯
    -2.91
    呖
    -2.91
    ⟣
    -2.88
     花纹
    -2.86
    POSITIVE LOGITS
    \
    3.36
     Both
    3.14
    am
    2.98
     These
    2.77
    {
    2.66
    ка
    2.56
    e
    2.53
    |$.
    2.50
     Set
    2.41
     Such
    2.41
    Activations Density 0.009%

    No Known Activations