© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2021
    Prev
    Next
    INDEX
    Explanations

    Rotary Positional Embeddings

    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_all/layer_41_width_262k_l0_big
    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
    ᵚ
    0.45
    炼
    0.40
    flatten
    0.39
    ামাক
    0.39
     സമൂ
    0.38
    өрд
    0.37
    Sweet
    0.37
    riche
    0.36
    炖
    0.36
    叠
    0.36
    POSITIVE LOGITS
     value
    0.48
     query
    0.47
     gate
    0.47
     expert
    0.47
     Value
    0.45
     key
    0.44
     rope
    0.44
     VALUE
    0.42
     revenue
    0.41
    GATE
    0.41
    Activations Density 0.006%

    No Known Activations