© 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. 257352
    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
    用い
    0.46
    族
    0.44
    ̠
    0.44
    Miranda
    0.43
    וי
    0.42
     זי
    0.42
    τ
    0.41
    츨
    0.41
    STEIN
    0.40
    Gonzalez
    0.40
    POSITIVE LOGITS
     decomposition
    0.57
    पना
    0.52
     decomposed
    0.52
     doable
    0.51
     predetermined
    0.50
     plag
    0.50
     preventive
    0.50
     promoting
    0.50
     node
    0.49
     fraudulent
    0.49
    Activations Density 0.005%

    No Known Activations