© 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. 10-GEMMASCOPE-RES-131K
    7. 57541
    Prev
    Next
    INDEX
    Explanations

    words starting with pro

    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_10/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
    锇
    -2.27
     frecuentemente
    -2.09
     dritte
    -2.09
     使っ
    -2.06
     obviamente
    -2.05
     fuertemente
    -2.02
     sequência
    -1.95
    <td>
    -1.91
     disminu
    -1.84
     supuestamente
    -1.84
    POSITIVE LOGITS
    蛧
    2.45
    a
    2.22
    峮
    2.19
    u
    2.06
    ၈
    2.00
     Kecil
    1.98
     also
    1.96
    เกง
    1.94
    軾
    1.92
    yards
    1.89
    Activations Density 0.011%

    No Known Activations