© 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. 53692
    Prev
    Next
    INDEX
    Explanations

    adverb or adjective followed by verb

    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
     nuestro
    0.54
     mój
    0.48
    ۸
    0.48
     нашем
    0.48
     kaun
    0.48
     naszej
    0.47
     gráf
    0.47
     unserem
    0.47
     répand
    0.46
    ۵
    0.46
    POSITIVE LOGITS
     belongings
    0.48
    ิ
    0.41
    ets
    0.40
    ิบ
    0.39
    ేవ
    0.39
    ాలు
    0.39
    ang
    0.38
    assets
    0.38
    ើស
    0.38
    重的
    0.37
    Activations Density 0.005%

    No Known Activations