© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 254823
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     splitting
    0.45
     pluripotent
    0.42
     atom
    0.41
     hepatocellular
    0.40
     buffering
    0.40
    .¹
    0.40
     demod
    0.40
     freezes
    0.39
    splitContainer
    0.39
    GBT
    0.39
    POSITIVE LOGITS
     ఇంటి
    0.50
     Mungkin
    0.48
     besuchen
    0.45
     semoga
    0.45
    不僅
    0.45
     模型
    0.45
     gør
    0.44
     modèle
    0.44
     बताएं
    0.44
     家
    0.43
    Activations Density 0.000%

    No Known Activations