© 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. 10-GEMMASCOPE-RES-131K
    4. 10171
    Prev
    Next
    INDEX
    Explanations

    Dear Bob, Air sorting

    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_10/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
    .
    -2.17
    If
    -2.08
    W
    -2.05
    The
    -1.92
    before
    -1.92
    With
    -1.90
     можете
    -1.87
    For
    -1.86
    Even
    -1.85
    Included
    -1.84
    POSITIVE LOGITS
     protože
    2.61
     to
    2.17
    を用
    2.05
     pretože
    1.83
     into
    1.79
    渽
    1.77
     they
    1.71
    はある
    1.69
     varför
    1.68
     což
    1.67
    Activations Density 0.001%

    No Known Activations