© 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. 87107
    Prev
    Next
    INDEX
    Explanations

    beach, surf, dune, ocean

    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
     mill
    -0.78
    biblioteca
    -0.76
    Proton
    -0.75
     lake
    -0.74
    uyer
    -0.73
    ()))
    -0.72
    itete
    -0.72
    checkable
    -0.71
     farmhouse
    -0.71
     cortical
    -0.71
    POSITIVE LOGITS
     beach
    1.15
     dune
    1.00
    beach
    0.98
     surf
    0.98
    Beach
    0.96
     dunes
    0.93
     strand
    0.93
     Dune
    0.92
     nourishment
    0.90
    strand
    0.89
    Activations Density 0.039%

    No Known Activations