© 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. 10-GEMMASCOPE-RES-131K
    7. 3734
    Prev
    Next
    INDEX
    Explanations

    word origins

    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_10/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
     with
    -1.64
    </i>
    -1.34
    𝖕
    -1.30
    氾
    -1.27
    Manfaat
    -1.27
     Funktionalität
    -1.27
     znal
    -1.23
     hijas
    -1.22
    occasione
    -1.21
    鑿
    -1.21
    POSITIVE LOGITS
     to
    1.52
     fleste
    1.28
     applau
    1.27
     Escribe
    1.27
     of
    1.25
     midt
    1.19
    ティブ
    1.18
    榈
    1.16
     frambo
    1.16
     Tipos
    1.16
    Activations Density 0.048%

    No Known Activations