© 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. 84374
    Prev
    Next
    INDEX
    Explanations

    magnetic conditions or names

    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
    ógica
    -0.74
     দ
    -0.71
     waiting
    -0.69
    受付
    -0.69
    ouble
    -0.67
    ཕ
    -0.67
    Locke
    -0.66
    multicolumn
    -0.66
    Secs
    -0.66
    Ɖ
    -0.65
    POSITIVE LOGITS
    Magnetic
    0.90
     magnetic
    0.89
     Magnetic
    0.88
    års
    0.83
     conditions
    0.79
    magnetic
    0.77
     وسط
    0.75
     affect
    0.73
     Aleksandra
    0.71
    アルコール
    0.70
    Activations Density 0.017%

    No Known Activations