© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 226778
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    modeling
    0.48
     ಕಬ್ಬಿಣ
    0.47
    ান্তে
    0.47
    bc
    0.45
    smöglichkeiten
    0.45
     \,\
    0.44
    м
    0.44
    ިއ
    0.43
     Бекер
    0.43
    general
    0.42
    POSITIVE LOGITS
     Colours
    0.47
    ナップ
    0.46
     footwear
    0.45
    િજા
    0.45
     snorkeling
    0.41
    "=>$
    0.41
    証明
    0.41
    ர்களுக்கு
    0.40
    鹳
    0.40
     giới
    0.40
    Activations Density 0.011%

    No Known Activations