© 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. 93287
    Prev
    Next
    INDEX
    Explanations

    javascript and css code

    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
     même
    -1.24
     from
    -1.17
     навіть
    -1.10
     rumahnya
    -1.07
     kochen
    -1.05
     scherm
    -1.04
     сті
    -1.00
    getBoard
    -0.99
     техні
    -0.98
     to
    -0.97
    POSITIVE LOGITS
    kowania
    1.19
     Coming
    1.15
    xed
    1.14
    ﻷ
    1.05
    爆笑
    1.05
    協議
    1.04
     Vereinbarung
    1.03
    隊長
    1.01
     funcione
    1.01
     khu
    1.01
    Activations Density 0.006%

    No Known Activations