© 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. 111466
    Prev
    Next
    INDEX
    Explanations

    darkness and silence

    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
    Lead
    0.50
     Rabu
    0.46
    ऊन
    0.46
     модуль
    0.44
    鬱
    0.43
     mivel
    0.43
     установка
    0.42
    軍
    0.42
     Juin
    0.42
    Red
    0.42
    POSITIVE LOGITS
    বিজ
    0.46
    ynd
    0.46
    once
    0.43
     rRNA
    0.43
    ণ্য
    0.43
     baggy
    0.43
    দৃশ্য
    0.43
    ənd
    0.42
    cellular
    0.42
    եք
    0.42
    Activations Density 0.002%

    No Known Activations