© 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. 103446
    Prev
    Next
    INDEX
    Explanations

    code structure

    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
     any
    -0.84
    であり
    -0.84
     different
    -0.83
     might
    -0.81
     offrire
    -0.79
     Different
    -0.79
     aanwezig
    -0.77
     numerous
    -0.76
     combined
    -0.75
    عض
    -0.75
    POSITIVE LOGITS
    nace
    0.90
    SIZ
    0.90
    LEN
    0.84
    Þ
    0.81
    EZ
    0.81
    illeurs
    0.81
    xin
    0.80
     dien
    0.79
    ALA
    0.79
    🔵
    0.79
    Activations Density 0.018%

    No Known Activations