© 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. 66373
    Prev
    Next
    INDEX
    Explanations

    prefixes leading to specific 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
     balcón
    -0.83
    kreises
    -0.76
     輪
    -0.75
    муж
    -0.74
    nictví
    -0.73
    FACES
    -0.73
    otent
    -0.72
    geschoss
    -0.71
    ेंद
    -0.70
    Lifecycle
    -0.69
    POSITIVE LOGITS
     phyto
    0.82
     verkle
    0.76
     iron
    0.76
     queso
    0.75
    redis
    0.73
    iron
    0.73
     тр
    0.71
     Stol
    0.71
     lok
    0.71
     tank
    0.71
    Activations Density 0.028%

    No Known Activations