© 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. 34693
    Prev
    Next
    INDEX
    Explanations

    technical terms and 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
    Ска
    -0.80
     like
    -0.79
     около
    -0.77
    Цена
    -0.73
     sugli
    -0.72
    Сред
    -0.71
     began
    -0.71
    mbles
    -0.69
    午後
    -0.68
     just
    -0.67
    POSITIVE LOGITS
     handel
    0.96
     widths
    0.92
     wider
    0.86
    widths
    0.85
     Pipeline
    0.85
    kanal
    0.84
    adaptation
    0.83
    DataOutputStream
    0.83
     pip
    0.82
     width
    0.82
    Activations Density 0.010%

    No Known Activations