© 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. 44375
    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
    悲伤
    -1.18
    类型的
    -1.11
    JBL
    -1.09
     avulla
    -1.09
    gelöst
    -1.08
    他們
    -1.07
    遗憾
    -1.05
    momo
    -1.05
    ▷
    -1.04
    莚
    -1.03
    POSITIVE LOGITS
     autoestima
    1.61
     tantas
    1.52
    全是
    1.51
    नलोड
    1.40
    巨大的
    1.37
    蕻
    1.35
     thorough
    1.32
    鸰
    1.32
    緇
    1.32
    なのでしょう
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.