© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15025
    Prev
    Next
    INDEX
    Explanations

    programming examples and keywords

    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
     sientes
    -1.58
    k
    -1.52
     manchmal
    -1.51
    x
    -1.40
     иногда
    -1.40
     hatte
    -1.30
     tuve
    -1.27
     ofreci
    -1.27
     одна
    -1.23
    pi
    -1.22
    POSITIVE LOGITS
     naše
    1.49
     tohoto
    1.47
    astos
    1.44
     like
    1.43
     图解
    1.40
     コレクション
    1.39
    jelaskan
    1.39
    вік
    1.38
     philippe
    1.38
    cakup
    1.38
    Activations Density 0.017%

    No Known Activations