© 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. 40-GEMMASCOPE-2-RES-262K
    7. 190991
    Prev
    Next
    INDEX
    Explanations

    past continuous actions and states

    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_40_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
    最近
    0.44
     давно
    0.42
     recientes
    0.41
    以上の
    0.40
     সেদিন
    0.40
    最初に
    0.40
    詁
    0.39
     bý
    0.39
     જે
    0.38
     உடனடியாக
    0.38
    POSITIVE LOGITS
     veniva
    0.73
     pouvait
    0.62
     pouvaient
    0.61
     kept
    0.58
     repeatedly
    0.56
     podían
    0.55
    kept
    0.52
     dawa
    0.52
     হচ্ছিল
    0.49
     tended
    0.49
    Activations Density 0.024%

    No Known Activations