© 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. 48117
    Prev
    Next
    INDEX
    Explanations

    Beverly Hills

    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
     can
    -0.78
    prm
    -0.76
     можна
    -0.75
    标
    -0.72
    Instance
    -0.71
    Werner
    -0.71
    HANDLE
    -0.71
    Handles
    -0.70
    "
    -0.69
    entro
    -0.66
    POSITIVE LOGITS
     HILLS
    1.22
     Hills
    1.19
     hills
    1.01
    hills
    0.95
    Hills
    0.88
    bria
    0.83
    Lundi
    0.79
    logen
    0.79
    ambassade
    0.78
    ⠀⠀
    0.77
    Activations Density 0.030%

    No Known Activations