© 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. 15247
    Prev
    Next
    INDEX
    Explanations

    similar size to Bengal Tigers

    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
     controvers
    0.52
     речь
    0.49
     лиш
    0.49
    __)
    0.48
     каче
    0.47
     torment
    0.46
     }{}_{\
    0.46
    изо
    0.45
     bicovariant
    0.44
     ક
    0.44
    POSITIVE LOGITS
    zhu
    0.45
     database
    0.45
    ab
    0.44
     organizations
    0.43
    数据库
    0.43
    发挥
    0.43
     databases
    0.43
    izz
    0.43
    graph
    0.43
    angel
    0.43
    Activations Density 0.003%

    No Known Activations