© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 501
    Prev
    Next
    INDEX
    Explanations

    best regards, thanks

    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
    Protection
    -0.90
    保护
    -0.86
     család
    -0.82
    守护
    -0.82
     مشروع
    -0.81
    Учитель
    -0.80
    𝒪
    -0.77
    lopp
    -0.77
     Protection
    -0.75
    Зна
    -0.75
    POSITIVE LOGITS
    Regards
    2.30
     Regards
    2.25
     regards
    2.11
     Best
    1.71
     regard
    1.70
     best
    1.70
    regards
    1.68
    Best
    1.50
     Kind
    1.50
    best
    1.49
    Activations Density 0.191%

    No Known Activations