© 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. 34-GEMMASCOPE-RES-131K
    7. 33738
    Prev
    Next
    INDEX
    Explanations

    last kind particular type

    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_34/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
    fordshire
    -1.30
    儛
    -1.30
     burbu
    -1.28
     diskusi
    -1.27
    cún
    -1.22
     sula
    -1.22
    givers
    -1.21
    isku
    -1.20
    蘩
    -1.20
    样子
    -1.19
    POSITIVE LOGITS
     last
    1.83
     kind
    1.68
     particular
    1.67
     type
    1.67
     derniers
    1.55
     laatste
    1.50
     latter
    1.50
     dernières
    1.36
     últimos
    1.32
     particulares
    1.30
    Activations Density 0.022%

    No Known Activations