© 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. 11404
    Prev
    Next
    INDEX
    Explanations

    approximate values and prices

    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
    ✳
    0.51
     удобно
    0.49
     wygod
    0.48
     cómoda
    0.47
    ﹙
    0.46
     cómod
    0.46
     kullanarak
    0.45
     vinculado
    0.45
    丶
    0.45
     ಕಾರ್
    0.45
    POSITIVE LOGITS
    ))
    0.45
    nader
    0.41
    pes
    0.40
     were
    0.40
    were
    0.40
    ologies
    0.38
     Fox
    0.38
     understood
    0.38
    fox
    0.38
     Centers
    0.38
    Activations Density 0.015%

    No Known Activations