© 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. 39811
    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
     akumulator
    -1.26
     supremely
    -1.16
     yesterday
    -1.10
    といふ
    -1.09
     has
    -1.09
    ｗｗ
    -1.08
     from
    -1.08
     Charles
    -1.05
    ñado
    -1.05
     енер
    -1.04
    POSITIVE LOGITS
     diferite
    1.45
    eventbus
    1.35
     escreveu
    1.34
    Когда
    1.24
    После
    1.24
     verschill
    1.23
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.23
     diferentes
    1.21
     aconteceu
    1.21
     terdiri
    1.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.