© 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. 111055
    Prev
    Next
    INDEX
    Explanations

    words starting with sch or ending with ributions

    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
    cognised
    -0.82
     Chee
    -0.81
    adeloupe
    -0.81
     النساء
    -0.78
    ствовал
    -0.77
     folgen
    -0.76
     muestre
    -0.76
    鹂
    -0.76
     vezet
    -0.75
     mendatang
    -0.75
    POSITIVE LOGITS
     succes
    0.76
    SID
    0.74
    Tenure
    0.73
    reicher
    0.69
    SUCCESS
    0.69
     popular
    0.67
     coal
    0.66
    Situation
    0.66
     kür
    0.66
    zadeh
    0.66
    Activations Density 0.037%

    No Known Activations