© 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-65K
    7. 48937
    Prev
    Next
    INDEX
    Explanations

    subject 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_65k_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
     overworked
    0.44
    มี
    0.43
     अप्र
    0.43
    estabelecimento
    0.41
    娌
    0.41
    મો
    0.38
     introductions
    0.38
     నిర్ణ
    0.38
     Wiesner
    0.38
     besonder
    0.37
    POSITIVE LOGITS
     utilizando
    0.39
     जागरूक
    0.39
    我国
    0.38
    cited
    0.37
    ໃຊ
    0.37
     يستخدم
    0.37
     Uses
    0.37
    cient
    0.37
    $,
    0.36
    benefits
    0.36
    Activations Density 0.001%

    No Known Activations