© 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. 90300
    Prev
    Next
    INDEX
    Explanations

    years and numerical ranges

    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
     only
    -2.47
     through
    -2.39
     from
    -2.31
     on
    -2.27
     because
    -2.23
     like
    -2.03
     just
    -2.02
     superbly
    -2.00
     can
    -1.98
     after
    -1.98
    POSITIVE LOGITS
    鷽
    2.03
     incrí
    1.93
     œufs
    1.91
     champignons
    1.89
     実例
    1.89
     ingrédients
    1.86
     apprécier
    1.84
    綃
    1.79
    atically
    1.77
     juger
    1.74
    Activations Density 0.044%

    No Known Activations