© 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. 16-GEMMASCOPE-2-RES-262K
    7. 109175
    Prev
    Next
    INDEX
    Explanations

    directions, building, influencing, election

    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_16_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
    lių
    0.51
    j
    0.49
    icht
    0.49
    opcode
    0.49
    ljiv
    0.49
    beans
    0.48
    癤
    0.48
     their
    0.48
    డా
    0.48
    ﺩ
    0.47
    POSITIVE LOGITS
    ուն
    0.49
    իտ
    0.47
    тую
    0.47
    ուս
    0.47
    之类的
    0.44
     Southerners
    0.43
    TaskPojo
    0.43
    тного
    0.43
     বরাবর
    0.42
     естественно
    0.42
    Activations Density 0.000%

    No Known Activations