© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3155
    Prev
    Next
    INDEX
    Explanations

    NLTK library and NLP tasks

    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_all/layer_41_width_262k_l0_big
    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
    routingHeader
    0.54
    ូត
    0.50
     répartition
    0.49
     agrícola
    0.49
    ngthen
    0.49
    هَا
    0.49
    ាតុ
    0.49
    ᔨ
    0.49
    ត់
    0.48
    otransfer
    0.47
    POSITIVE LOGITS
     nltk
    1.25
    nltk
    1.15
     stopwords
    1.01
     NLP
    0.88
     Corpus
    0.86
    stopwords
    0.85
    NLP
    0.84
     Word
    0.81
     Stop
    0.81
     stop
    0.80
    Activations Density 0.006%

    No Known Activations