© 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. 10-GEMMASCOPE-RES-131K
    4. 11074
    Prev
    Next
    INDEX
    Explanations

    discrete increments or stages

    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
     résine
    -1.35
    }
    -1.34
     étan
    -1.29
     Etwas
    -1.27
     Apesar
    -1.26
     puissante
    -1.26
     cuivre
    -1.20
    &
    -1.20
     Porém
    -1.18
    {
    -1.18
    POSITIVE LOGITS
     my
    1.33
    ceis
    1.30
    ността
    1.27
    Now
    1.27
    JTextArea
    1.25
     reliant
    1.24
     viele
    1.23
     step
    1.20
    adhe
    1.19
     iniciativas
    1.18
    Activations Density 0.038%

    No Known Activations