© 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. 22-GEMMASCOPE-RES-131K
    4. 104587
    Prev
    Next
    INDEX
    Explanations

    starting words and their follow-ups

    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_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
    Since
    -0.98
    Depuis
    -0.91
    娲
    -0.84
     corpora
    -0.80
    fortawesome
    -0.79
    Besides
    -0.77
    ṓ
    -0.77
    mités
    -0.76
     Prologue
    -0.74
     this
    -0.74
    POSITIVE LOGITS
    НГ
    0.96
    λιά
    0.90
    кви
    0.90
    耵
    0.85
     réalisateur
    0.85
     ванной
    0.83
     Institutionen
    0.83
     rallado
    0.82
    ВС
    0.82
    θηκαν
    0.82
    Activations Density 0.000%

    No Known Activations