© 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. 64164
    Prev
    Next
    INDEX
    Explanations

    sunglasses, technology, areas

    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
    1
    0.61
    4
    0.48
    си
    0.46
    ха
    0.46
    becue
    0.45
    бер
    0.43
    mannschaft
    0.43
    д
    0.43
     belliger
    0.42
    2
    0.41
    POSITIVE LOGITS
     thống
    0.47
     khuôn
    0.47
     보험
    0.46
    烔
    0.46
     vattum
    0.45
    湋
    0.45
    鹖
    0.44
     teknologi
    0.44
    帏
    0.44
     lantai
    0.43
    Activations Density 0.006%

    No Known Activations