© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11200
    Prev
    Next
    INDEX
    Explanations

    language processing and linguistics

    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_16k_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
    辂
    0.49
    лата
    0.48
    Reform
    0.45
    liery
    0.45
    Phot
    0.43
    चु
    0.43
    袷
    0.42
    嵇
    0.42
    ંત્રણ
    0.41
    钩
    0.41
    POSITIVE LOGITS
     NLP
    0.90
     nltk
    0.90
    nltk
    0.89
    ngram
    0.82
    nlp
    0.80
     linguistic
    0.80
     linguistics
    0.79
    NLP
    0.79
     vocabulary
    0.78
     lexical
    0.77
    Activations Density 0.771%

    No Known Activations