© 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. 41541
    Prev
    Next
    INDEX
    Explanations

    clinical studies

    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
    邾
    0.51
    ศาส
    0.48
    бле
    0.47
    measurable
    0.47
    บาง
    0.45
    笳
    0.44
    ავი
    0.43
     ಕಾ
    0.43
    мя
    0.43
    անակ
    0.43
    POSITIVE LOGITS
    ),
    0.51
    )
    0.51
    la
    0.50
     Winters
    0.48
     sumo
    0.48
     playroom
    0.46
    t
    0.46
    d
    0.45
     rapides
    0.45
     BuzzFeed
    0.44
    Activations Density 0.000%

    No Known Activations