© 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. 34-GEMMASCOPE-RES-131K
    4. 90645
    Prev
    Next
    INDEX
    Explanations

    code, file paths, or documentation

    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
     because
    -0.85
     essential
    -0.85
     sekal
    -0.84
     cautious
    -0.82
    veien
    -0.81
     horrific
    -0.81
    Mittel
    -0.81
     first
    -0.80
     Pflanzen
    -0.80
     utterly
    -0.79
    POSITIVE LOGITS
    Watch
    1.12
    watch
    1.06
     Watch
    1.05
     watch
    0.97
     Kelowna
    0.90
     есть
    0.90
    ufs
    0.89
    oneof
    0.89
     WATCH
    0.88
    ография
    0.88
    Activations Density 0.004%

    No Known Activations