© 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-262K
    7. 10223
    Prev
    Next
    INDEX
    Explanations

    ambitious, negotiation, understand

    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_262k_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
    .​
    0.24
    します
    0.22
     روی
    0.21
    。
    0.21
     linearly
    0.20
     ​
    0.20
     devem
    0.20
     senescence
    0.20
    ↵
    0.20
    دی
    0.20
    POSITIVE LOGITS
     автомобиль
    0.27
     коричне
    0.26
    é
    0.26
    ព
    0.25
     различни
    0.25
    Если
    0.25
     ఒక
    0.25
    这是一个
    0.25
     автомобилей
    0.24
     когда
    0.24
    Activations Density 0.174%

    No Known Activations