© 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. 48244
    Prev
    Next
    INDEX
    Explanations

    lost civilizations, sunken places

    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
    步
    -0.77
    VIAF
    -0.77
     Forrest
    -0.77
    genomen
    -0.76
    isons
    -0.75
     модер
    -0.73
     Bever
    -0.72
    Villa
    -0.72
    zzazione
    -0.72
    江
    -0.72
    POSITIVE LOGITS
     Atlantis
    1.77
    Atlan
    1.42
     Atlan
    1.18
     sunken
    1.17
     submer
    1.06
    lante
    1.00
     допо
    0.97
     submerged
    0.96
     survivors
    0.93
     lost
    0.92
    Activations Density 0.023%

    No Known Activations