© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47674
    Prev
    Next
    INDEX
    Explanations

    descriptive noun-verb collocations

    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
     its
    -0.92
     vital
    -0.90
     universities
    -0.88
     an
    -0.86
     good
    -0.84
     two
    -0.80
     university
    -0.80
     tästä
    -0.80
     claras
    -0.80
     uñas
    -0.79
    POSITIVE LOGITS
    才是
    0.97
     devast
    0.96
    一心
    0.94
    größern
    0.90
    ίκη
    0.87
    秒
    0.86
     cuit
    0.86
     achat
    0.86
     asfalto
    0.86
     praticamente
    0.85
    Activations Density 0.100%

    No Known Activations