© 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. 252220
    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
     क्लोरीन
    0.47
    ilder
    0.46
     clima
    0.46
     climate
    0.45
     plas
    0.44
     fé
    0.42
     Trafford
    0.41
    氈
    0.41
    ферен
    0.40
     climat
    0.40
    POSITIVE LOGITS
    n
    0.52
    irli
    0.50
    ن
    0.50
    irsi
    0.49
    ні
    0.48
     অন্তর্ভুক্ত
    0.48
    fourth
    0.47
    区块
    0.47
    enciais
    0.46
    Repeating
    0.46
    Activations Density 0.000%

    No Known Activations