© 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. 118433
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     Lista
    -0.80
    人気の
    -0.77
     binder
    -0.76
    paraíso
    -0.74
    永恒
    -0.73
    USO
    -0.73
     pronunci
    -0.73
    联网
    -0.71
    怎么做
    -0.71
     dat
    -0.71
    POSITIVE LOGITS
     smelling
    0.92
    point
    0.88
     Spiegel
    0.84
    motion
    0.84
     verrà
    0.81
    POINT
    0.81
     parteci
    0.81
     代码
    0.80
     doveva
    0.80
    ствен
    0.79
    Activations Density 0.040%

    No Known Activations