© 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. 123730
    Prev
    Next
    INDEX
    Explanations

    Stanford University and related

    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
     So
    -2.31
     l
    -2.30
     Mereka
    -2.23
     Jednak
    -2.22
     rundown
    -2.22
     With
    -2.22
     This
    -2.19
     Selain
    -2.14
     They
    -2.13
     Apalagi
    -2.13
    POSITIVE LOGITS
    :”
    3.00
     唯美
    2.77
    <td>
    2.77
    觔
    2.53
    婓
    2.52
    the
    2.50
    ではまた
    2.48
    ”
    2.47
     sebagai
    2.45
    ”?
    2.41
    Activations Density 0.004%

    No Known Activations