© 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. 21428
    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
    0
    -1.44
    为什么会
    -1.43
     UIAlert
    -1.37
     adesivo
    -1.36
     berço
    -1.32
    想了想
    -1.31
     décrire
    -1.30
     spearheaded
    -1.30
    畱
    -1.30
     complimented
    -1.29
    POSITIVE LOGITS
    During
    1.39
     That
    1.39
     essential
    1.30
    ⩽
    1.27
     “
    1.25
     Also
    1.20
    These
    1.20
    </h4>
    1.17
    焦点
    1.16
    Every
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.