© 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. 34-GEMMASCOPE-RES-131K
    7. 653
    Prev
    Next
    INDEX
    Explanations

    forms compound words

    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_34/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
     poliéster
    -0.98
     سپس
    -0.93
    therapie
    -0.92
    Meld
    -0.88
     rechange
    -0.88
     débuts
    -0.87
    ❢
    -0.87
     évé
    -0.86
    ――――
    -0.85
    лық
    -0.85
    POSITIVE LOGITS
     but
    0.91
    ......
    0.85
    findOneAndUpdate
    0.85
    的中
    0.82
    …..
    0.82
     себе
    0.82
    rceil
    0.81
    ….
    0.80
    egd
    0.80
    .....
    0.79
    Activations Density 0.000%

    No Known Activations