© 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. 89972
    Prev
    Next
    INDEX
    Explanations

    neutron and related physics terms

    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
    摸
    -0.80
     microsoft
    -0.68
     angeboten
    -0.66
     Aftermath
    -0.65
     integriert
    -0.65
     neumáticos
    -0.65
     Juventud
    -0.65
     IFC
    -0.65
     جواب
    -0.65
    𝑗
    -0.64
    POSITIVE LOGITS
    ける
    0.81
     neutron
    0.81
    kop
    0.75
     Pau
    0.72
     Neutron
    0.70
    startAnimation
    0.69
    Asimismo
    0.69
    нула
    0.68
    gento
    0.68
    neutron
    0.68
    Activations Density 0.051%

    No Known Activations