© 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-65K
    7. 36053
    Prev
    Next
    INDEX
    Explanations

    do something with 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_65k_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
    Automatically
    0.41
    Adopt
    0.38
     UNICEF
    0.38
    喂
    0.38
    Training
    0.37
    以便
    0.37
     Cable
    0.37
     उद्यान
    0.36
    ანს
    0.36
    鏻
    0.36
    POSITIVE LOGITS
     અથવા
    0.55
     yoki
    0.55
    比如说
    0.50
     veya
    0.49
     eller
    0.49
     alguna
    0.49
     mesela
    0.49
    比如說
    0.48
     alebo
    0.48
     bijvoorbeeld
    0.48
    Activations Density 0.160%

    No Known Activations