© 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. 9691
    Prev
    Next
    INDEX
    Explanations

    ASCII ranges, letters, digits

    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
     for
    -2.09
     or
    -1.99
     and
    -1.90
     solusi
    -1.39
    ',"
    -1.38
     of
    -1.37
    ¡¡
    -1.35
    🎶
    -1.34
     jugadores
    -1.30
    😶
    -1.28
    POSITIVE LOGITS
    を探す
    1.61
     erwähnten
    1.59
    还不错
    1.53
     peggio
    1.52
     raffredd
    1.50
    3
    1.48
     merav
    1.47
    5
    1.41
     riscal
    1.39
     chłod
    1.38
    Activations Density 0.029%

    No Known Activations