© 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. 51475
    Prev
    Next
    INDEX
    Explanations

    new introductions

    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
    ↵
    0.50
    ften
    0.46
    ophe
    0.45
     oor
    0.45
     preven
    0.45
     ontwikkelen
    0.44
     geweest
    0.43
     vaiht
    0.43
    <0xE2>
    0.42
     evaluar
    0.42
    POSITIVE LOGITS
    اً
    0.56
    다
    0.54
     सेल्सियस
    0.53
    ている
    0.48
    ത്തും
    0.48
    اا
    0.48
     котором
    0.46
    Ǘ
    0.45
    риал
    0.45
    сят
    0.44
    Activations Density 0.017%

    No Known Activations