© 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. 9788
    Prev
    Next
    INDEX
    Explanations

    list delimiters

    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
     just
    -0.88
    ága
    -0.85
     simpel
    -0.85
     sogar
    -0.83
     essentially
    -0.80
    ição
    -0.79
     Even
    -0.79
     Saltar
    -0.77
     from
    -0.76
     və
    -0.76
    POSITIVE LOGITS
    cds
    0.98
     aproximativ
    0.94
     การ
    0.89
     میزان
    0.89
    それでも
    0.89
    度に
    0.88
     sonunda
    0.88
     แต่
    0.88
     distinctive
    0.87
     but
    0.86
    Activations Density 0.061%

    No Known Activations