© 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. 102425
    Prev
    Next
    INDEX
    Explanations

    scientific and programming terms

    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
     medial
    -0.67
    Baltimore
    -0.66
    Busca
    -0.66
     känna
    -0.65
    னை
    -0.65
     licensed
    -0.63
    聂
    -0.63
     сере
    -0.62
     unlicensed
    -0.62
     Martian
    -0.61
    POSITIVE LOGITS
     TL
    1.03
    mother
    0.98
     MOTHER
    0.95
     Mothers
    0.88
     mothers
    0.88
     kandid
    0.88
    lodash
    0.87
     daughters
    0.87
    Lore
    0.86
    atisfactory
    0.86
    Activations Density 0.015%

    No Known Activations