© 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. 72857
    Prev
    Next
    INDEX
    Explanations

    TODO lists and tasks

    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
    是她
    -1.95
    </b>
    -1.92
    flam
    -1.88
    蓠
    -1.86
     gebeten
    -1.86
     erste
    -1.85
     svil
    -1.84
    enerys
    -1.83
     oluşan
    -1.82
     linken
    -1.79
    POSITIVE LOGITS
     henvis
    1.87
    as
    1.87
    塤
    1.84
    سبة
    1.76
     and
    1.73
     earnestly
    1.71
     Sociedade
    1.70
     Administração
    1.69
    火焰
    1.67
    浤
    1.63
    Activations Density 0.004%

    No Known Activations