© 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. 22-GEMMASCOPE-RES-131K
    7. 92957
    Prev
    Next
    INDEX
    Explanations

    Excelling, Dual-peak, Complete

    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_22/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
     specific
    -1.11
     spørs
    -1.11
     because
    -1.10
     which
    -1.08
     or
    -1.06
     from
    -1.06
     frequently
    -1.05
     first
    -1.03
     generally
    -1.02
     perhaps
    -1.00
    POSITIVE LOGITS
     mês
    1.14
     เรา
    1.13
    ícias
    1.07
     blessures
    1.05
     Há
    1.05
    مدیر
    1.02
     comunicare
    1.02
     moeten
    1.02
     abbiamo
    1.02
    COMPR
    1.01
    Activations Density 0.001%

    No Known Activations