© 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. 27262
    Prev
    Next
    INDEX
    Explanations

    specific keywords followed by punctuation

    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
     அழி
    0.41
    😡
    0.41
     impover
    0.40
     desperately
    0.40
     meu
    0.38
     Dataset
    0.38
    践
    0.38
     tome
    0.37
    Boot
    0.37
    Dé
    0.37
    POSITIVE LOGITS
     каждого
    0.45
    ными
    0.44
    ంలోని
    0.43
    𝐛
    0.43
    ль
    0.43
    部分
    0.42
    hosting
    0.42
    customers
    0.41
    estas
    0.41
     каждой
    0.41
    Activations Density 0.025%

    No Known Activations