© 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. 50173
    Prev
    Next
    INDEX
    Explanations

    astronomical and scientific terms

    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
    र्य
    -0.75
    cov
    -0.70
    闹
    -0.69
     verhe
    -0.68
    ности
    -0.68
    昇
    -0.67
    uckle
    -0.66
    扶
    -0.65
     flare
    -0.65
    월
    -0.65
    POSITIVE LOGITS
    ffions
    1.07
     Bubbles
    0.80
     exacto
    0.79
     powietrza
    0.78
     northwest
    0.78
     northeast
    0.76
    こちらは
    0.75
     REQUIRE
    0.74
     ejec
    0.74
     Playa
    0.73
    Activations Density 0.014%

    No Known Activations