© 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. 22-GEMMASCOPE-RES-131K
    4. 39836
    Prev
    Next
    INDEX
    Explanations

    seeking information or clarification

    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_22/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
    ⸫
    -0.91
     fabrique
    -0.90
    blick
    -0.90
    結論
    -0.89
     شنبه
    -0.88
    imetry
    -0.84
    ラフ
    -0.82
     vidare
    -0.81
    Вывод
    -0.81
    setValue
    -0.81
    POSITIVE LOGITS
     their
    1.23
     whether
    1.02
     explicitly
    1.02
     each
    1.00
     carefully
    0.93
     before
    0.92
     asked
    0.91
    判断
    0.88
     test
    0.87
     ask
    0.87
    Activations Density 0.068%

    No Known Activations