© 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. 5340
    Prev
    Next
    INDEX
    Explanations

    intensifiers followed by descriptors

    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
     중에
    0.22
     在
    0.21
     tại
    0.21
     사용
    0.20
     Than
    0.20
     Và
    0.20
    ："
    0.19
     तपाई
    0.19
     vasena
    0.19
    を
    0.19
    POSITIVE LOGITS
     tenuous
    0.23
     grueling
    0.23
     dismal
    0.23
     ingenious
    0.22
     ambitious
    0.22
    重要な
    0.22
     subtle
    0.22
     lucrative
    0.22
     realist
    0.22
     গুরুত্বপূর্ণ
    0.22
    Activations Density 0.793%

    No Known Activations