© 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. 71393
    Prev
    Next
    INDEX
    Explanations

    code snippets and software documentation

    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
     häls
    -1.09
     tends
    -1.06
     predomin
    -1.05
     робота
    -1.02
     provides
    -1.00
    Ừ
    -1.00
    Sabato
    -0.99
    كتشاف
    -0.98
    鑿
    -0.97
     föränd
    -0.96
    POSITIVE LOGITS
     zwi
    1.31
     desglose
    1.20
     gier
    1.15
     repuesto
    1.13
     großartige
    1.11
     kompatibel
    1.09
     sorprender
    1.05
    seamnă
    1.05
     vollständige
    1.05
     integran
    1.05
    Activations Density 0.004%

    No Known Activations