© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12009
    Prev
    Next
    INDEX
    Explanations

    earth followed by specific concepts

    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
    unload
    -0.79
    这也
    -0.74
    そうですが
    -0.73
    もあります
    -0.73
    ierungs
    -0.72
    Incon
    -0.72
    但在
    -0.71
    過ごす
    -0.71
    もちろん
    -0.69
    cjs
    -0.69
    POSITIVE LOGITS
     earth
    1.16
     shattering
    1.06
     sciences
    1.05
     Earth
    1.05
    quate
    1.02
    worm
    1.01
    Earth
    0.99
    moving
    0.97
    shat
    0.93
     EARTH
    0.91
    Activations Density 0.009%

    No Known Activations