© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109309
    Prev
    Next
    INDEX
    Explanations

    singer Inger Lorre

    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
     Interests
    -0.86
     indien
    -0.81
     ill
    -0.79
     diku
    -0.78
    Prem
    -0.77
     idk
    -0.76
    VDC
    -0.76
    檎
    -0.76
    难题
    -0.71
     расти
    -0.70
    POSITIVE LOGITS
    ANGLE
    0.81
    攵
    0.78
    懶
    0.78
    ผิด
    0.76
    estar
    0.75
     actualizaciones
    0.74
     Euphrates
    0.73
    而在
    0.71
     entailed
    0.71
     Vz
    0.70
    Activations Density 0.142%

    No Known Activations