© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62713
    Prev
    Next
    INDEX
    Explanations

    breakup neutron source

    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
    opponent
    -0.77
     opponent
    -0.72
    ⓣ
    -0.70
    őzés
    -0.70
    احب
    -0.70
    pide
    -0.69
    klis
    -0.69
    鍔
    -0.69
    río
    -0.69
     Demp
    -0.69
    POSITIVE LOGITS
     unbound
    1.22
     bound
    1.15
    Bound
    1.11
     Bound
    0.94
    bound
    0.88
     Bor
    0.87
    binding
    0.82
     Triton
    0.82
     breakup
    0.82
    roxene
    0.81
    Activations Density 0.035%

    No Known Activations