© 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. 75297
    Prev
    Next
    INDEX
    Explanations

    like followed by a comparison

    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
    4
    -2.20
    6
    -1.85
     of
    -1.83
    in
    -1.81
    1
    -1.77
    9
    -1.69
    唷
    -1.63
    呦
    -1.63
    From
    -1.61
    Some
    -1.58
    POSITIVE LOGITS
     România
    1.74
     obliga
    1.73
     enrique
    1.71
     pulsa
    1.69
     araba
    1.68
    を使用した
    1.68
    effectively
    1.66
     イラストレーション
    1.66
     amada
    1.61
     masaj
    1.61
    Activations Density 0.012%

    No Known Activations