© 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. 60730
    Prev
    Next
    INDEX
    Explanations

    referred to as

    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
    んですが
    -1.02
     поки
    -0.91
     който
    -0.90
     двигатель
    -0.88
     linkovi
    -0.86
    菲律
    -0.86
    𝟮
    -0.86
    bilirsiniz
    -0.85
     răng
    -0.85
    檔案
    -0.85
    POSITIVE LOGITS
     chrétienne
    1.27
    IER
    1.20
    了很多
    1.12
    itting
    1.11
    nasi
    1.09
    ICA
    1.07
    
    1.07
    ient
    1.07
    thodoxy
    1.07
    ADO
    1.06
    Activations Density 0.250%

    No Known Activations