© 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. 101306
    Prev
    Next
    INDEX
    Explanations

    color, materials, medicine

    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
    徵
    0.45
     దృష్టి
    0.44
     pure
    0.43
     言
    0.43
     블
    0.42
    噰
    0.42
     겸
    0.42
    採取
    0.41
    overe
    0.41
     সাহিত্য
    0.40
    POSITIVE LOGITS
     cuando
    0.49
     ellos
    0.45
    جي
    0.44
     entonces
    0.43
     transferencia
    0.43
    Concat
    0.42
     compliqué
    0.42
     Cuando
    0.41
     drugim
    0.41
    Leftrightarrow
    0.41
    Activations Density 0.001%

    No Known Activations