© 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. 92472
    Prev
    Next
    INDEX
    Explanations

    claimed invention

    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
    Observer
    -0.86
    观的
    -0.84
    After
    -0.82
    endaftar
    -0.81
     After
    -0.79
     six
    -0.79
     Unterhaltung
    -0.79
    Not
    -0.79
    悲伤
    -0.79
     bool
    -0.77
    POSITIVE LOGITS
    ルム
    0.96
     cadastro
    0.95
     Newtown
    0.94
    núť
    0.92
    requested
    0.91
     Paralympic
    0.90
     nila
    0.89
    isiaj
    0.89
    /');
    0.88
     cana
    0.88
    Activations Density 0.001%

    No Known Activations