© 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. 18895
    Prev
    Next
    INDEX
    Explanations

    classification metrics and structured data

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    し
    0.41
    리아
    0.40
    레
    0.39
     kys
    0.38
    Week
    0.36
     че
    0.36
    keys
    0.35
    ÃO
    0.35
    Comput
    0.35
    há
    0.34
    POSITIVE LOGITS
    ammlung
    0.47
                                  
    0.44
    iftoire
    0.44
     Franck
    0.43
    🎑
    0.43
    ädt
    0.43
     Bluff
    0.41
     thirteenth
    0.40
                                   
    0.40
     dispoz
    0.40
    Activations Density 0.007%

    No Known Activations