© 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. 90961
    Prev
    Next
    INDEX
    Explanations

    organization abbreviations and company names

    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
     their
    -1.60
     их
    -1.21
    zdo
    -1.17
     leur
    -1.13
    鬟
    -1.12
     jejich
    -1.11
    Número
    -1.10
    该公司
    -1.09
     їх
    -1.08
    Depois
    -1.08
    POSITIVE LOGITS
     staff
    1.38
     products
    1.35
    com
    1.27
     employees
    1.20
     customers
    1.16
     deutschland
    1.16
    ni
    1.16
     frauen
    1.16
    da
    1.15
     policies
    1.15
    Activations Density 0.097%

    No Known Activations