© 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. 97945
    Prev
    Next
    INDEX
    Explanations

    recipes and ingredients

    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
     mexicano
    -1.09
     cubano
    -0.96
    thai
    -0.95
     thai
    -0.91
     Mexicano
    -0.90
    Amigos
    -0.88
    ोड़
    -0.88
    ኦ
    -0.86
    🌮
    -0.85
     crores
    -0.85
    POSITIVE LOGITS
     sepol
    0.89
     nazionale
    0.88
     gait
    0.84
     uniquely
    0.84
     Typically
    0.83
    棵
    0.82
     cittadino
    0.82
    احبه
    0.81
    ${
    0.79
     segreto
    0.79
    Activations Density 0.013%

    No Known Activations