© 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. 10-GEMMASCOPE-RES-131K
    7. 104625
    Prev
    Next
    INDEX
    Explanations

    different or differences

    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
    峩
    -1.63
     музе
    -1.56
     to
    -1.53
     progression
    -1.52
     друзьями
    -1.38
     avait
    -1.36
    ྃ
    -1.33
     bonne
    -1.32
    вгений
    -1.32
    很大的
    -1.31
    POSITIVE LOGITS
     know
    1.89
     understand
    1.71
     how
    1.71
     contribuir
    1.69
    ільки
    1.60
     разные
    1.56
     didn
    1.55
     dedicar
    1.51
     about
    1.49
     limitado
    1.48
    Activations Density 0.059%

    No Known Activations