© 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. 58674
    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
     how
    -1.04
     our
    -0.96
     zweiter
    -0.89
    ông
    -0.86
     organisiert
    -0.86
     sogar
    -0.85
     み
    -0.85
     extiende
    -0.84
     equipada
    -0.84
     ఈ
    -0.83
    POSITIVE LOGITS
     reiv
    1.07
    Trinidad
    0.95
     capitalismo
    0.95
    舔
    0.93
    ズニー
    0.93
     PRINCIP
    0.93
     Гали
    0.92
    Sieg
    0.92
     GUY
    0.91
     azok
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.