© 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. 1787
    Prev
    Next
    INDEX
    Explanations

    one followed by word

    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
    0
    -4.91
    4
    -3.44
     '
    -3.00
    6
    -2.91
    5
    -2.91
    7
    -2.81
    3
    -2.81
    2
    -2.80
    9
    -2.78
    8
    -2.77
    POSITIVE LOGITS
    棪
    3.31
    ámica
    2.86
    塤
    2.70
    浤
    2.69
     případě
    2.58
    utterstock
    2.56
    瀦
    2.50
    ruzione
    2.48
    伷
    2.48
    旰
    2.47
    Activations Density 0.175%

    No Known Activations