© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6826
    Prev
    Next
    INDEX
    Explanations

    multi company, division, warehouse

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

    customer status and lifetime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Patreon
    0.59
    🧠
    0.55
    cloudinary
    0.54
    unsplash
    0.54
    👾
    0.53
    cloudflare
    0.53
    oldown
    0.51
    stagram
    0.51
    🖕
    0.50
     あなた
    0.50
    POSITIVE LOGITS
    TypeCode
    0.82
     Remarks
    0.68
    costcenter
    0.67
     SAP
    0.65
     lookup
    0.64
    Remarks
    0.64
     debtor
    0.62
     effective
    0.61
     codes
    0.61
     workflow
    0.61
    Activations Density 0.077%

    No Known Activations