© 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. 12628
    Prev
    Next
    INDEX
    Explanations

    mutable programming constructs

    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
    ↵
    -2.73
     The
    -2.70
    </strong>
    -2.45
    鲠
    -2.22
    躄
    -2.13
     прежде
    -2.11
    .
    -2.06
    ':
    -2.00
     aqueles
    -1.96
    周围
    -1.94
    POSITIVE LOGITS
    が
    2.61
     réservé
    2.59
     extremadamente
    2.41
    (
    2.38
     énergé
    2.36
     eşofman
    2.34
    、『
    2.30
    ｏ
    2.25
     orgánico
    2.25
     japonaise
    2.25
    Activations Density 0.002%

    No Known Activations