© 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. 103489
    Prev
    Next
    INDEX
    Explanations

    University Elles, starter Taylor, count 1

    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
     می‌گو
    -1.50
     descubre
    -1.20
     AND
    -1.18
    —
    -1.18
    with
    -1.13
     statunit
    -1.13
     encontrou
    -1.12
     lembra
    -1.09
     gostar
    -1.05
     mostrou
    -1.05
    POSITIVE LOGITS
    兩
    2.41
    利
    2.36
    金
    2.30
    來
    2.11
    論
    1.95
     ſer
    1.75
    ώ
    1.66
    ÊNCIAS
    1.55
    不
    1.52
    阳台
    1.51
    Activations Density 0.068%

    No Known Activations