© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73646
    Prev
    Next
    INDEX
    Explanations

    explains meaning or origin

    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
    ícias
    -1.33
    ִּ
    -1.18
     navigu
    -1.16
     Θε
    -1.15
    Maak
    -1.13
    ּוֹ
    -1.13
     فرص
    -1.10
     우리
    -1.09
    isters
    -1.09
     информация
    -1.07
    POSITIVE LOGITS
     ویتامین
    1.27
     with
    1.20
     s
    1.19
     has
    1.14
     of
    1.10
     for
    1.05
    <i>
    1.03
    >
    1.02
     to
    1.02
    だそうです
    1.01
    Activations Density 0.012%

    No Known Activations