© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    especially significant disrepair

    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
     сотрудни
    -1.23
    حر
    -1.21
    μαν
    -1.15
    дивиду
    -1.11
     molho
    -1.05
    Außerdem
    -1.05
    getField
    -1.05
     
    -1.02
    maru
    -1.02
    MENT
    -1.02
    POSITIVE LOGITS
     insbesondere
    1.16
     рекомендую
    1.16
     (~
    1.16
     наверное
    1.15
     umumnya
    1.15
     erfolgt
    1.15
    =============
    1.13
     ~$
    1.11
    seattle
    1.09
    修炼
    1.08
    Activations Density 0.542%

    No Known Activations