© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49351
    Prev
    Next
    INDEX
    Explanations

    language learning institute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     read
    -0.73
    BagConstraints
    -0.72
    做
    -0.69
     insensible
    -0.68
    作战
    -0.66
    今まで
    -0.65
     Briefs
    -0.64
     footed
    -0.63
     Eurasian
    -0.63
     đầy
    -0.63
    POSITIVE LOGITS
     IELTS
    1.34
     language
    1.30
     TOEFL
    1.28
     English
    1.22
     lingu
    1.19
     Sprach
    1.19
     ESL
    1.16
     homestay
    1.14
     язы
    1.09
     linguistic
    1.06
    Activations Density 0.013%

    No Known Activations