© 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. 34-GEMMASCOPE-RES-131K
    7. 25984
    Prev
    Next
    INDEX
    Explanations

    permissions and license

    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
    Flip
    -0.70
     Flip
    -0.69
    平台
    -0.68
    }>
    -0.68
    第二天
    -0.68
    डा
    -0.68
    <h4>
    -0.68
    Zip
    -0.66
    بيت
    -0.66
    GT
    -0.65
    POSITIVE LOGITS
     Ха
    0.77
    aix
    0.70
    surgery
    0.67
    tring
    0.67
     campuses
    0.66
     Queen
    0.66
    ッシ
    0.64
     queen
    0.63
     QUEEN
    0.63
     Syna
    0.61
    Activations Density 0.064%

    No Known Activations