© 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. 57273
    Prev
    Next
    INDEX
    Explanations

    viewport width

    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
     serums
    0.43
     lactic
    0.43
     bronchitis
    0.40
     middlemen
    0.40
    ﮢ
    0.39
    Es
    0.39
    ඖ
    0.38
     probiotics
    0.38
     neglects
    0.38
     fibre
    0.37
    POSITIVE LOGITS
    燵
    0.42
     свободы
    0.41
    ORGE
    0.41
    ప్రత్యర్థి
    0.40
     empêcher
    0.39
     dépasse
    0.39
     correspondant
    0.39
    ницей
    0.38
     особенностей
    0.38
     επέ
    0.38
    Activations Density 0.001%

    No Known Activations