© 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. 10-GEMMASCOPE-RES-131K
    7. 113366
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    1
    -2.39
    ཋ
    -2.33
     It
    -2.28
    تیجه
    -2.23
     They
    -2.17
    0
    -2.08
    Only
    -1.91
    </h3>
    -1.91
     delve
    -1.91
    ਲ਼
    -1.90
    POSITIVE LOGITS
    饜
    2.92
    踽
    2.92
    mml
    2.81
    摀
    2.75
    沵
    2.53
    
    2.45
    龗
    2.41
    嚶
    2.39
     diza
    2.34
    ⁓
    2.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.