© 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. 10-GEMMASCOPE-RES-131K
    7. 110556
    Prev
    Next
    INDEX
    Explanations

    quoted text

    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
     was
    -2.70
     detects
    -2.48
     ventured
    -2.36
    丏
    -2.28
     mantém
    -2.27
     employs
    -2.23
     objected
    -2.23
    ar
    -2.23
    '
    -2.22
    LEBR
    -2.20
    POSITIVE LOGITS
     نے
    2.27
    ,”
    2.27
     客厅
    2.25
     and
    2.23
    ’,
    2.22
    <td>
    2.20
     丁目
    2.16
    骜
    2.13
     (“
    2.08
    .
    2.08
    Activations Density 0.001%

    No Known Activations