© 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. 73599
    Prev
    Next
    INDEX
    Explanations

    fairy tales references, mining, and reflections

    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
    köping
    -0.75
     pelaksanaan
    -0.74
    ulement
    -0.73
     memainkan
    -0.71
    cycline
    -0.69
     convirtió
    -0.69
    achio
    -0.68
    ৎ
    -0.68
    ICLES
    -0.68
    Held
    -0.68
    POSITIVE LOGITS
     dwarfs
    1.30
     Dwar
    1.24
     fairest
    1.15
     Faire
    1.09
     mining
    1.07
     miners
    1.07
     Mining
    1.06
     Miners
    1.05
     dwarf
    1.04
     Mirror
    1.03
    Activations Density 0.026%

    No Known Activations