© 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. 50143
    Prev
    Next
    INDEX
    Explanations

    put away

    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
     Horne
    -0.79
     Gauthier
    -0.73
    묻
    -0.71
    foreach
    -0.70
    ianza
    -0.68
    يميديا
    -0.67
     berühm
    -0.67
    ้าน
    -0.66
     ausz
    -0.66
     выйти
    -0.65
    POSITIVE LOGITS
     away
    8.69
    Away
    5.56
     Away
    5.28
    away
    5.09
     AWAY
    4.19
    AWAY
    4.13
    eaway
    3.09
    taway
    2.66
    aways
    2.36
     weg
    2.30
    Activations Density 0.093%

    No Known Activations