© 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. 82730
    Prev
    Next
    INDEX
    Explanations

    quantities and names

    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
    Liefs
    -0.94
    なに
    -0.94
    Ɛ
    -0.90
    いわゆる
    -0.87
    MutableLiveData
    -0.87
    esteld
    -0.86
     даже
    -0.85
     Meto
    -0.85
     or
    -0.84
    мето
    -0.84
    POSITIVE LOGITS
     school
    1.05
     novin
    0.98
     '
    0.94
     =
    0.91
     odpor
    0.90
    omial
    0.90
     fewer
    0.88
     oči
    0.88
     vean
    0.87
    amplific
    0.87
    Activations Density 0.038%

    No Known Activations