© 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. 3189
    Prev
    Next
    INDEX
    Explanations

    caves and karst landscapes

    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
     Detox
    -0.81
    ataire
    -0.80
     gelombang
    -0.77
    ório
    -0.75
     sə
    -0.74
     kona
    -0.74
    ゲット
    -0.73
    codename
    -0.72
     detox
    -0.72
    槁
    -0.71
    POSITIVE LOGITS
     cave
    2.55
     caves
    1.98
     Cave
    1.77
    cave
    1.69
    Cave
    1.55
     Caves
    1.48
    洞
    1.40
     grotte
    1.25
     spel
    1.16
     cavern
    1.16
    Activations Density 0.048%

    No Known Activations