© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11008
    Prev
    Next
    INDEX
    Explanations

    entity definitions and data structures

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to business or organizational entities and services (like orders, customers, hotels, bookings, payments, trips).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     this
    -1.33
    和
    -1.30
     are
    -1.21
     cantora
    -1.20
     Wikipédia
    -1.17
    脍
    -1.16
     VIAF
    -1.16
     atriz
    -1.13
    Verlag
    -1.13
     BUREAU
    -1.12
    POSITIVE LOGITS
     betrifft
    1.36
    便利です
    1.34
     reason
    1.30
    <bos>
    1.28
     AMAZING
    1.27
    幾天
    1.27
     gerichtet
    1.27
    锇
    1.24
    イツ
    1.20
     according
    1.19
    Activations Density 0.077%

    No Known Activations