© 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. 54063
    Prev
    Next
    INDEX
    Explanations

    expressing thanks to everyone

    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
     when
    -1.47
     künftig
    -1.35
     information
    -1.33
     after
    -1.33
    dicionado
    -1.32
    ך
    -1.32
    ()]
    -1.31
    膾
    -1.20
     a
    -1.15
    сшта
    -1.12
    POSITIVE LOGITS
     the
    1.90
     everyone
    1.69
    everyone
    1.50
     all
    1.44
    every
    1.38
    すべての
    1.36
     всички
    1.34
    那些
    1.33
     جميع
    1.27
     those
    1.26
    Activations Density 0.012%

    No Known Activations