© 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. 118535
    Prev
    Next
    INDEX
    Explanations

    width proportions, percentages, or divisions

    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
    CardBody
    -0.82
    rière
    -0.82
     steg
    -0.81
    Также
    -0.79
    깊
    -0.78
     també
    -0.77
     bohater
    -0.77
    ɭ
    -0.77
    ㅎ
    -0.77
    zyć
    -0.76
    POSITIVE LOGITS
     half
    1.20
     left
    1.06
     evenly
    0.96
     Left
    0.91
    Left
    0.90
    left
    0.89
     splitting
    0.88
     کوتاه
    0.88
     part
    0.86
     short
    0.86
    Activations Density 0.014%

    No Known Activations