© 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. 86261
    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
     a
    -1.20
    Styrene
    -0.97
    せよ
    -0.94
    Barium
    -0.93
     distinct
    -0.93
     東京都
    -0.90
     孩子
    -0.90
     gli
    -0.89
    prnewswire
    -0.89
    ########.
    -0.88
    POSITIVE LOGITS
     apariencia
    0.96
     extiende
    0.94
     this
    0.94
    渡辺
    0.91
     chegar
    0.91
    ⑸
    0.91
     chiamato
    0.89
     isolé
    0.89
    adhé
    0.89
    metter
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.