© 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. 22-GEMMASCOPE-RES-131K
    7. 73872
    Prev
    Next
    INDEX
    Explanations

    disregard for things

    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_22/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
    どうしても
    -0.97
    wania
    -0.93
     politico
    -0.92
     chaque
    -0.90
    biamo
    -0.90
    ᄃ
    -0.89
     Natura
    -0.87
    nessy
    -0.87
     accompagné
    -0.87
    笄
    -0.86
    POSITIVE LOGITS
     even
    1.26
     consequences
    1.14
    lcccccc
    1.05
     anything
    1.00
     даже
    0.98
     nawet
    0.98
    ύτε
    0.96
    有任何
    0.94
     considerations
    0.93
     any
    0.92
    Activations Density 0.031%

    No Known Activations