© 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. 461
    Prev
    Next
    INDEX
    Explanations

    to introduce a purpose or consequence

    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
     emisiones
    -1.59
     lentejuelas
    -1.45
     pieles
    -1.44
     macetas
    -1.43
     tracción
    -1.34
     burbujas
    -1.32
     acogedor
    -1.31
     capucha
    -1.29
     botines
    -1.28
     being
    -1.27
    POSITIVE LOGITS
     to
    5.38
    เพื่อ
    3.28
     чтобы
    3.03
     כדי
    2.73
     để
    2.64
     nhằm
    2.64
     afin
    2.53
     hoping
    2.52
     เพื่อ
    2.27
     in
    2.09
    Activations Density 0.230%

    No Known Activations