© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9011
    Prev
    Next
    INDEX
    Explanations

    memory lane, offending keys, occurring levels

    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
    return
    -1.67
    </td>
    -1.63
    ↵↵↵
    -1.56
     ________
    -1.40
     sapat
    -1.38
     récla
    -1.36
    </h5>
    -1.34
     _________
    -1.34
     réaliser
    -1.31
     représenter
    -1.31
    POSITIVE LOGITS
     on
    2.00
    蒟
    1.48
    水墨
    1.48
    terness
    1.46
     at
    1.43
     его
    1.41
     tény
    1.39
    桔
    1.39
     sentado
    1.38
    炅
    1.38
    Activations Density 0.161%

    No Known Activations