© 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. 79517
    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
    ocks
    -1.19
    while
    -1.13
     for
    -1.12
     burch
    -1.08
     schal
    -1.05
    }>{
    -1.02
     >",
    -1.01
    olarmente
    -0.99
    meisters
    -0.98
     March
    -0.98
    POSITIVE LOGITS
     besucht
    1.26
    さあ
    1.22
    ＊＊＊
    1.22
    すみません
    1.21
    ardı
    1.18
    あなたは
    1.16
    さぁ
    1.15
    感じが
    1.15
    感じです
    1.14
    えっ
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.