© 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. 80014
    Prev
    Next
    INDEX
    Explanations

    events and information

    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
     пище
    -1.34
     katholischen
    -1.32
     cukru
    -1.31
    Tienen
    -1.30
     children
    -1.28
     christlichen
    -1.27
     lokalen
    -1.25
     speziellen
    -1.23
     иллюстрация
    -1.23
     گیاه
    -1.23
    POSITIVE LOGITS
    ּוֹ
    1.73
    ִּ
    1.55
    ַּ
    1.53
    ֶּ
    1.45
    ansı
    1.43
    ְּ
    1.42
     your
    1.40
     бампер
    1.30
    וּ
    1.27
    zensionen
    1.27
    Activations Density 0.086%

    No Known Activations