© 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. 10-GEMMASCOPE-RES-131K
    7. 119983
    Prev
    Next
    INDEX
    Explanations

    institutional or organizational roles

    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_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
     everywhere
    -1.25
     will
    -1.22
     there
    -1.19
     like
    -1.17
     vanaf
    -1.15
     ਅਤੇ
    -1.15
    ｷ
    -1.13
    튿
    -1.09
     něco
    -1.06
     häufigsten
    -1.06
    POSITIVE LOGITS
     where
    1.27
     sekunder
    1.13
     лишь
    1.12
     their
    1.12
    nossa
    1.08
    一
    1.05
     poderia
    1.05
    **/
    1.05
    关于
    1.03
    半
    1.01
    Activations Density 0.223%

    No Known Activations