© 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. 94113
    Prev
    Next
    INDEX
    Explanations

    repository pattern

    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
     service
    -1.19
    service
    -1.04
    ilm
    -0.93
     services
    -0.88
     serviço
    -0.85
     intelligence
    -0.81
     SERVICE
    -0.81
    intelligence
    -0.80
     sân
    -0.79
     SERVICES
    -0.78
    POSITIVE LOGITS
    ధ
    0.78
    APPED
    0.77
    었다
    0.76
    SECT
    0.76
     CMC
    0.74
    返
    0.74
     セットアップ
    0.73
     vitu
    0.71
    leftarrow
    0.71
    ítica
    0.70
    Activations Density 0.006%

    No Known Activations