© 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. 130556
    Prev
    Next
    INDEX
    Explanations

    Objective-C Foundation imports

    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
     borracha
    -1.23
    〢
    -1.21
     Acesso
    -1.20
    elektron
    -1.18
     about
    -1.16
    recen
    -1.15
     desapar
    -1.10
     produjo
    -1.10
     viewed
    -1.09
    slika
    -1.09
    POSITIVE LOGITS
    起来的
    1.27
     <",
    1.27
     >=",
    1.25
    on
    1.25
    などの
    1.17
    搅拌
    1.16
    飙
    1.16
    يكي
    1.16
                         
    1.15
    uscular
    1.14
    Activations Density 0.001%

    No Known Activations