© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40621
    Prev
    Next
    INDEX
    Explanations

    particle decays and transitions

    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
    
    -1.67
    使った
    -1.47
    踹
    -1.45
     usando
    -1.44
    なども
    -1.43
    issauga
    -1.40
    ag
    -1.39
    ⏑
    -1.38
    你先
    -1.38
     localización
    -1.36
    POSITIVE LOGITS
     with
    1.95
     With
    1.73
    Rüyada
    1.71
     Having
    1.66
     any
    1.66
     Knowing
    1.66
     to
    1.63
     so
    1.59
     Normally
    1.59
     Combining
    1.56
    Activations Density 0.058%

    No Known Activations