© 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. 67447
    Prev
    Next
    INDEX
    Explanations

    programming contexts

    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
     their
    -1.49
     because
    -1.21
     for
    -1.12
     during
    -1.06
     equipe
    -1.05
     only
    -1.04
     several
    -1.04
     litro
    -1.00
     out
    -0.99
     aros
    -0.97
    POSITIVE LOGITS
     fervent
    0.92
    ailleurs
    0.88
     således
    0.87
     vgl
    0.86
     répar
    0.85
    共有
    0.85
     gummy
    0.85
     kormány
    0.85
     somit
    0.84
    Nj
    0.83
    Activations Density 0.011%

    No Known Activations