© 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. 9843
    Prev
    Next
    INDEX
    Explanations

    absence of

    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
     same
    -1.90
     munc
    -1.54
    挥手
    -1.54
     imobili
    -1.51
     comanda
    -1.50
     borde
    -1.48
     violon
    -1.48
     facilita
    -1.48
     perfecte
    -1.47
     Poids
    -1.45
    POSITIVE LOGITS
    This
    2.09
    2
    1.93
    Semoga
    1.86
     []:
    1.60
    郝
    1.59
    懨
    1.58
    that
    1.56
    Pozdrawiam
    1.53
    ที่จะ
    1.46
     Einige
    1.45
    Activations Density 0.033%

    No Known Activations