© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 245037
    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
    ěru
    0.50
    سبوع
    0.49
    稒
    0.45
    をはじめ
    0.45
    Hundreds
    0.44
    Thousands
    0.44
     milhares
    0.44
    BtnFill
    0.44
     کرکے
    0.43
    勒
    0.43
    POSITIVE LOGITS
     uses
    0.44
     deductive
    0.43
     denominado
    0.42
     CAN
    0.40
     preferentially
    0.40
    可能有
    0.38
     discretized
    0.38
     deber
    0.38
     manager
    0.37
    sv
    0.37
    Activations Density 0.004%

    No Known Activations