© 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. 13797
    Prev
    Next
    INDEX
    Explanations

    sharing links with promotion

    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
    Toponymie
    -1.02
    forEach
    -0.98
    hradun
    -0.94
     Polskiej
    -0.94
     razie
    -0.94
    []
    -0.93
    gerät
    -0.93
     Exteriores
    -0.93
     Uniwersyte
    -0.91
     Bioaccumulative
    -0.91
    POSITIVE LOGITS
     our
    1.38
     executar
    1.13
     content
    1.13
     carregar
    1.10
    rupal
    1.06
     mercredi
    1.06
    了出去
    1.06
    ㌔
    1.06
    Припев
    1.05
     accompagner
    1.03
    Activations Density 0.038%

    No Known Activations