© 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. 4295
    Prev
    Next
    INDEX
    Explanations

    exploring new adventures and places

    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
    şağı
    -0.97
     برخی
    -0.96
    itate
    -0.92
     Longfellow
    -0.92
    inske
    -0.90
     prefeitura
    -0.90
     Bourgoin
    -0.90
     getAccount
    -0.87
    letics
    -0.87
    τως
    -0.86
    POSITIVE LOGITS
     new
    3.66
     different
    3.63
    different
    2.69
    new
    2.41
    Different
    2.30
     diferentes
    2.25
    不同的
    2.25
     Different
    2.20
     разные
    2.13
     interesting
    2.03
    Activations Density 0.053%

    No Known Activations