© 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. 12065
    Prev
    Next
    INDEX
    Explanations

    old age or old name

    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
     "
    -3.13
    絝
    -2.42
     continúas
    -2.39
     некото
    -2.19
    >
    -2.16
     -
    -2.09
    ’
    -2.08
    なのですが
    -2.08
    になりますが
    -2.06
     procurando
    -1.98
    POSITIVE LOGITS
     fashioned
    4.31
     یا
    2.91
    或
    2.80
    杁
    2.61
     Luglio
    2.53
     fotografico
    2.53
     Giugno
    2.53
    、
    2.50
     perdana
    2.45
     Gennaio
    2.45
    Activations Density 0.038%

    No Known Activations