© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78979
    Prev
    Next
    INDEX
    Explanations

    listing following items

    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
     both
    -0.95
     REPRESENTATIVES
    -0.85
    ǃ
    -0.83
     despite
    -0.82
     straips
    -0.80
     not
    -0.80
    zają
    -0.80
     veterin
    -0.79
     Despite
    -0.79
     mara
    -0.79
    POSITIVE LOGITS
     [],
    0.87
     ‌
    0.82
    などが
    0.80
     умер
    0.80
    centration
    0.79
     bleak
    0.79
     تأ
    0.78
    </blockquote>
    0.76
     Herbs
    0.75
     ähnlichen
    0.75
    Activations Density 0.004%

    No Known Activations