© 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. 92507
    Prev
    Next
    INDEX
    Explanations

    seeking help or treatment

    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
     تقوم
    -0.72
    kou
    -0.72
    ल्क
    -0.71
    スレ
    -0.69
    cc
    -0.69
    lanze
    -0.69
     banane
    -0.68
     iş
    -0.68
     broderie
    -0.68
    addCell
    -0.68
    POSITIVE LOGITS
     seek
    4.63
     seeking
    4.50
    seeking
    3.81
    Seeking
    3.67
    seek
    3.67
     Seeking
    3.64
     Seek
    3.61
    Seek
    3.48
     seeks
    3.47
     sought
    3.39
    Activations Density 0.128%

    No Known Activations