© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48571
    Prev
    Next
    INDEX
    Explanations

    Rams, LA, or names like Ramsey

    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
     ترک
    -0.79
     Bihar
    -0.76
    Vil
    -0.75
     Ebola
    -0.75
    quests
    -0.71
    履
    -0.71
     Lynx
    -0.71
    uccino
    -0.70
     distribuir
    -0.70
     moms
    -0.69
    POSITIVE LOGITS
     Rams
    1.33
    Rams
    1.18
    🐏
    1.05
     Ram
    0.93
     RAM
    0.87
     LA
    0.83
    Ram
    0.82
    RAM
    0.82
    Ĭ
    0.80
     planejamento
    0.79
    Activations Density 0.011%

    No Known Activations