© 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. 41262
    Prev
    Next
    INDEX
    Explanations

    3G mobile technology

    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
    蹓
    -2.05
    筺
    -1.94
    ꜆
    -1.93
    書いた
    -1.91
    
    -1.91
    梠
    -1.91
    そういえば
    -1.83
    "$_
    -1.80
    衚
    -1.80
    𝄆
    -1.79
    POSITIVE LOGITS
    .
    2.30
     тот
    1.96
    :
    1.86
    、
    1.71
    ))
    1.71
     обеспечивает
    1.70
     diligence
    1.67
     -
    1.66
    ’
    1.65
    izing
    1.59
    Activations Density 0.009%

    No Known Activations