© 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. 22436
    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
     來
    -2.53
     帶
    -2.36
     邊
    -2.34
     戰
    -2.27
    With
    -2.25
     别
    -2.16
    ſelves
    -2.09
     馆
    -2.08
    Every
    -2.08
    Also
    -2.08
    POSITIVE LOGITS
    '
    2.58
    跸
    2.56
    ing
    2.50
    ’
    2.42
    饧
    2.42
     ™
    2.11
     '
    2.05
     —
    2.03
    小朋友
    2.03
     I
    2.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.