© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73357
    Prev
    Next
    INDEX
    Explanations

    what do you/we/I

    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
    可以
    -2.63
     is
    -2.56
     –
    -2.41
    在
    -2.17
    '
    -2.03
    {
    -1.95
    如果
    -1.95
     -
    -1.95
     were
    -1.91
    只有
    -1.90
    POSITIVE LOGITS
     they
    2.91
     you
    2.77
     we
    2.64
    的那个
    2.42
    轵
    2.38
    妧
    2.17
    拊
    2.08
    ٳ
    2.08
    的那种
    2.08
    什么的
    2.08
    Activations Density 0.030%

    No Known Activations