© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195150
    Prev
    Next
    INDEX
    Explanations

    phrases with specific following words

    np_acts-logits-general · gemini-2.5-flash-lite

    Task Manager or Activity Monitor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sonra
    0.53
     skoro
    0.50
    h
    0.49
     minh
    0.49
     in
    0.49
    Kafka
    0.49
     ক্ষয়ক্ষ
    0.49
     §§
    0.48
     hầu
    0.48
    G
    0.47
    POSITIVE LOGITS
    issaient
    0.47
    ियस
    0.46
    زی
    0.45
     सिंग
    0.45
    आईएस
    0.45
    の花
    0.43
    დნენ
    0.43
    ಲು
    0.42
    isted
    0.42
     نمایش
    0.42
    Activations Density 0.001%

    No Known Activations