© 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. 6345
    Prev
    Next
    INDEX
    Explanations

    measurement or quantity

    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
    ().
    0.24
     convolutional
    0.24
    (),
    0.23
     {
    0.23
    文字列
    0.23
     regex
    0.22
     />
    0.22
     +=
    0.21
     whose
    0.21
                    
    0.21
    POSITIVE LOGITS
    Dried
    0.22
     dike
    0.21
    饮食
    0.21
     옷
    0.21
    Waters
    0.20
    饴
    0.20
    흡
    0.20
     earthen
    0.20
    Dry
    0.19
     tắm
    0.19
    Activations Density 0.001%

    No Known Activations