© 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. 4109
    Prev
    Next
    INDEX
    Explanations

    formal names of organizations and acts

    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
    胭
    0.25
     झाल्यावर
    0.24
    勇敢
    0.24
    ရင်
    0.23
     Justiça
    0.23
     trò
    0.22
     cantante
    0.22
     justiça
    0.22
    कांच्या
    0.21
     nỗi
    0.21
    POSITIVE LOGITS
    」
    0.29
     അ
    0.27
    ↵↵
    0.26
    \]
    0.26
     Г
    0.26
    」、
    0.25
     А
    0.25
     শীর্ষক
    0.25
    】
    0.25
     مت
    0.24
    Activations Density 0.328%

    No Known Activations