© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54243
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     действия
    -0.89
     PyTuple
    -0.85
     deres
    -0.85
     deras
    -0.82
    Delta
    -0.79
    额
    -0.79
    frontmatter
    -0.79
     их
    -0.78
    臨床
    -0.78
    了承
    -0.77
    POSITIVE LOGITS
     here
    1.22
    ➘
    1.06
    淫
    1.04
    formatting
    1.00
    ftar
    1.00
    cetamol
    0.98
     ácidos
    0.98
     esperienza
    0.97
     that
    0.96
     him
    0.96
    Activations Density 0.000%

    No Known Activations