© 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. 23929
    Prev
    Next
    INDEX
    Explanations

    social media actions

    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
    cupertino
    -0.89
    ous
    -0.84
    并非
    -0.84
    vaccinated
    -0.81
    balanceOf
    -0.80
     Whigs
    -0.80
    readlines
    -0.80
    ঢ
    -0.79
    odziel
    -0.79
    mp
    -0.79
    POSITIVE LOGITS
     and
    1.43
     this
    1.17
     it
    1.07
    และ
    0.99
    ボタン
    0.96
     comment
    0.95
    chaise
    0.93
     komentar
    0.91
    +")
    0.89
     or
    0.89
    Activations Density 0.036%

    No Known Activations