© 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. 61495
    Prev
    Next
    INDEX
    Explanations

    code and mathematical expressions

    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
    0
    -3.17
    ations
    -2.63
    Our
    -2.56
    ")
    -2.50
    Basically
    -2.48
     sudadera
    -2.39
    =
    -2.38
    蚍
    -2.38
    事も
    -2.34
    We
    -2.33
    POSITIVE LOGITS
     that
    3.30
    胧
    3.16
     these
    3.06
    𓆸
    2.78
     are
    2.77
     those
    2.72
    䊏
    2.67
    龙头
    2.64
     both
    2.63
    妘
    2.63
    Activations Density 0.002%

    No Known Activations