© 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. 27139
    Prev
    Next
    INDEX
    Explanations

    recursive function calls

    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
    Acetic
    0.44
    য়
    0.44
    Lastly
    0.44
     Lastly
    0.43
     Vial
    0.43
    Brightness
    0.42
     ganske
    0.42
    헹
    0.41
     biodegrad
    0.40
     sogen
    0.40
    POSITIVE LOGITS
     निर्मित
    0.43
     годом
    0.41
     εμφαν
    0.41
    DOMAIN
    0.40
     அவற்றை
    0.40
     व्यापार
    0.39
    存在
    0.39
    公司
    0.39
     globalization
    0.38
    機関
    0.38
    Activations Density 0.001%

    No Known Activations