© 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. 130538
    Prev
    Next
    INDEX
    Explanations

    the first to third

    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
     RECOMM
    -1.07
     favoris
    -1.05
     alſo
    -1.05
    toHaveBeen
    -1.03
     appétit
    -0.99
     interrom
    -0.98
    quran
    -0.96
     itali
    -0.96
     AllAfrica
    -0.95
     struktur
    -0.95
    POSITIVE LOGITS
     one
    1.45
     could
    1.34
     part
    1.33
     among
    1.28
    はその
    1.23
     included
    1.20
     thereunder
    1.14
     daarvan
    1.13
     incluida
    1.09
    其中的
    1.09
    Activations Density 0.067%

    No Known Activations