© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119128
    Prev
    Next
    INDEX
    Explanations

    text starting phrases

    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
     kän
    -0.73
    čkou
    -0.73
    soo
    -0.73
     overzicht
    -0.72
     跳转至
    -0.72
     hii
    -0.71
     araw
    -0.71
    Aro
    -0.70
    prés
    -0.69
     nader
    -0.69
    POSITIVE LOGITS
    OVERALL
    0.82
    Overall
    0.81
     Overall
    0.81
    涯
    0.80
    释
    0.77
    odan
    0.76
    MultipartFile
    0.76
    เอง
    0.75
     carrière
    0.75
    Klik
    0.74
    Activations Density 0.006%

    No Known Activations