© 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. 60131
    Prev
    Next
    INDEX
    Explanations

    geophysical research letters

    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
    Feat
    -0.76
    édrale
    -0.73
    atuor
    -0.73
     nara
    -0.72
    minent
    -0.71
    Ķ
    -0.71
    claimer
    -0.71
    場合があります
    -0.70
     Waldo
    -0.69
    IComponent
    -0.68
    POSITIVE LOGITS
    AGU
    0.98
     AGU
    0.91
     Reggie
    0.86
     ček
    0.81
     Zeng
    0.75
    🕛
    0.75
    Somos
    0.75
     Geophys
    0.75
     chaff
    0.75
    cci
    0.74
    Activations Density 0.006%

    No Known Activations