© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66194
    Prev
    Next
    INDEX
    Explanations

    costs, accounting, assets

    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
     dzied
    -1.13
    vocations
    -1.11
    brigens
    -1.00
    İŞ
    -0.99
     финан
    -0.98
     먹
    -0.98
     abaste
    -0.97
     viac
    -0.96
    gadier
    -0.93
     дописавши
    -0.93
    POSITIVE LOGITS
     accounting
    1.41
     impairment
    1.34
     items
    1.26
     assets
    1.26
     balances
    1.25
     Company
    1.23
     earnings
    1.21
     balance
    1.19
    pairment
    1.16
     income
    1.15
    Activations Density 0.042%

    No Known Activations