© 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. 58696
    Prev
    Next
    INDEX
    Explanations

    sociability and joint ventures

    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
    ༀ
    -2.89
    .
    -2.84
    尨
    -2.80
    趼
    -2.80
     is
    -2.73
     \
    -2.63
    拮
    -2.58
    阄
    -2.52
    聍
    -2.50
    脔
    -2.48
    POSITIVE LOGITS
    秾
    2.84
    女孩子
    2.84
     стал
    2.83
     dueños
    2.80
    栳
    2.77
     hopelessly
    2.75
    냑
    2.61
    うれ
    2.58
     hotly
    2.53
    小孩子
    2.52
    Activations Density 0.014%

    No Known Activations