© 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. 65156
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     hav
    -2.02
     and
    -1.96
    .”
    -1.95
    慙
    -1.77
     prochaines
    -1.73
     ebbe
    -1.69
    CHREIB
    -1.66
    gezogen
    -1.66
     ELIZABETH
    -1.65
    ﮑ
    -1.63
    POSITIVE LOGITS
     of
    3.02
    ritage
    1.81
     November
    1.80
     даже
    1.80
     We
    1.78
     December
    1.76
     Both
    1.76
    PasswordEncoder
    1.74
     other
    1.73
     in
    1.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.