© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66793
    Prev
    Next
    INDEX
    Explanations

    have options/opportunity

    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
     how
    -1.87
     even
    -1.63
     those
    -1.59
     is
    -1.45
     where
    -1.36
    Even
    -1.35
     by
    -1.35
    <i>
    -1.30
     why
    -1.28
     There
    -1.25
    POSITIVE LOGITS
     "',
    1.58
     options
    1.54
     opportunity
    1.49
    谞
    1.48
     seçenek
    1.48
    )$/,
    1.38
    ٦
    1.34
     Telerik
    1.34
     müm
    1.34
     possibility
    1.32
    Activations Density 0.097%

    No Known Activations