© 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. 48650
    Prev
    Next
    INDEX
    Explanations

    NHS, Soviet, Beach, Cloud

    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
     o
    0.47
    :
    0.45
     )
    0.45
     ا
    0.43
     A
    0.42
     delle
    0.41
     queste
    0.40
     tych
    0.40
    ของ
    0.40
    Anche
    0.40
    POSITIVE LOGITS
     개념
    0.45
    全体の
    0.41
    奬
    0.41
     ethos
    0.40
    ંત્ર
    0.39
    לי
    0.39
     전체
    0.38
     কাঠামো
    0.38
    ॅम्प
    0.38
     प्रणाली
    0.38
    Activations Density 0.040%

    No Known Activations