© 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. 61147
    Prev
    Next
    INDEX
    Explanations

    numbers followed by optional characters

    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
     "
    -1.89
    Unlike
    -1.58
     這
    -1.56
    These
    -1.55
    Both
    -1.52
     How
    -1.51
     However
    -1.48
    All
    -1.48
    After
    -1.45
     Как
    -1.42
    POSITIVE LOGITS
    縯
    1.60
    jenige
    1.59
     today
    1.51
    ╹
    1.48
    咈
    1.45
    chées
    1.45
    лением
    1.43
    扨
    1.41
     vanligt
    1.39
     توانند
    1.39
    Activations Density 0.006%

    No Known Activations