© 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. 12827
    Prev
    Next
    INDEX
    Explanations

    referencing text within documents

    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
     to
    0.68
     at
    0.55
    -
    0.53
    da
    0.51
    gu
    0.50
    bi
    0.49
    ↵↵
    0.49
     of
    0.49
    uffs
    0.48
     l
    0.47
    POSITIVE LOGITS
    ใน
    0.70
     dalam
    0.67
    장
    0.59
    dalam
    0.59
     katika
    0.59
    Dalam
    0.59
     trong
    0.57
     فونیټ
    0.53
     указа
    0.52
    ו
    0.52
    Activations Density 0.059%

    No Known Activations