© 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. 34-GEMMASCOPE-RES-131K
    4. 83729
    Prev
    Next
    INDEX
    Explanations

    you're able to

    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
    scaron
    -1.09
    </tr>
    -1.05
    thodoxy
    -1.00
     trouvé
    -0.96
    losti
    -0.96
     mentre
    -0.96
    思议
    -0.96
    ète
    -0.95
    देश
    -0.95
    aneity
    -0.94
    POSITIVE LOGITS
     able
    1.46
     in
    1.31
     greeted
    1.27
     guaranteed
    1.23
     advised
    1.20
     encouraged
    1.20
     warned
    1.16
     likely
    1.13
    vula
    1.03
     файлы
    1.03
    Activations Density 0.039%

    No Known Activations