© 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-16K
    7. 11795
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

    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
    ể
    0.43
    લ્ડ
    0.43
    ່
    0.42
    !",
    0.42
    ্যস্ত
    0.41
    osz
    0.40
    явля
    0.40
     étoile
    0.40
    λογή
    0.40
    ጬ
    0.40
    POSITIVE LOGITS
    拉克
    0.50
     ملاقات
    0.45
     syntactic
    0.43
     oov
    0.42
    UREMENT
    0.41
    URI
    0.41
    JSON
    0.40
    ULAR
    0.40
     laptops
    0.40
    合成
    0.40
    Activations Density 0.053%

    No Known Activations