© 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. 41969
    Prev
    Next
    INDEX
    Explanations

    preference for

    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
     eight
    -2.28
     six
    -2.09
     hundreds
    -2.00
    ’，
    -1.91
     three
    -1.91
     großes
    -1.85
     many
    -1.83
    掟
    -1.83
     spurred
    -1.83
     nine
    -1.80
    POSITIVE LOGITS
    ay
    2.03
    ሖ
    1.95
    0
    1.89
     какую
    1.84
    usions
    1.82
    Remember
    1.81
    henswürdigkeiten
    1.80
    created
    1.78
    ano
    1.77
    这种
    1.74
    Activations Density 0.003%

    No Known Activations