© 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. 103969
    Prev
    Next
    INDEX
    Explanations

    setup code

    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
     söyle
    -0.84
     siting
    -0.75
    したこと
    -0.74
    jh
    -0.73
     meanwhile
    -0.73
     прошлого
    -0.71
     aussit
    -0.70
    StartCoroutine
    -0.70
     視
    -0.70
     menores
    -0.69
    POSITIVE LOGITS
     dados
    0.83
    XmlAccessorType
    0.82
    ExtendWith
    0.81
     keli
    0.79
    onedDateTime
    0.79
     provoc
    0.77
     resonances
    0.77
     transpiration
    0.77
     transporters
    0.77
    ẵn
    0.76
    Activations Density 0.021%

    No Known Activations