© 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. 33166
    Prev
    Next
    INDEX
    Explanations

    attracting attention and entities

    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
    りましたが
    -0.91
     adquirido
    -0.90
    Accessor
    -0.90
    siempre
    -0.89
    Terima
    -0.88
     baloncesto
    -0.88
    強調
    -0.85
     ори
    -0.85
    expensive
    -0.85
    复古
    -0.85
    POSITIVE LOGITS
     attention
    2.19
    attention
    1.52
    Attention
    1.41
     Attention
    1.37
     внимание
    1.35
     crowds
    1.28
     perhatian
    1.26
     customers
    1.23
     into
    1.19
    注意
    1.18
    Activations Density 0.026%

    No Known Activations