© 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. 107403
    Prev
    Next
    INDEX
    Explanations

    spec_helper or rails_helper

    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
     різних
    -1.05
    这样一个
    -0.91
    してみた
    -0.90
    ってみた
    -0.88
    ssohn
    -0.88
    [],
    -0.85
     müm
    -0.84
     росій
    -0.83
    doppel
    -0.82
     ausgezeichnet
    -0.81
    POSITIVE LOGITS
     helper
    1.26
    helper
    1.22
     help
    0.96
    Helper
    0.95
    equalTo
    0.88
     helpers
    0.87
     או
    0.85
    Fuß
    0.83
     trợ
    0.83
     помощ
    0.83
    Activations Density 0.034%

    No Known Activations