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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15931
    Prev
    Next
    INDEX
    Explanations

    describing states or conditions

    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_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
     illetve
    0.46
    /
    0.46
     notoriously
    0.44
     drastic
    0.42
    的一些
    0.42
     varies
    0.41
    变
    0.41
    一些
    0.41
    ↵↵↵
    0.40
     некоторых
    0.40
    POSITIVE LOGITS
     असताना
    0.54
    当时
    0.53
     ketika
    0.50
    だったので
    0.48
    なかったので
    0.48
    當時
    0.47
     gewesen
    0.47
     estaba
    0.47
     थीं
    0.47
     damals
    0.46
    Activations Density 0.016%

    No Known Activations