© 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-16K
    7. 417
    Prev
    Next
    INDEX
    Explanations

    series finale remains

    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_16k_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
     содержания
    0.54
    ங்களுக்கு
    0.49
    बी
    0.47
    ピアノ
    0.47
    )}(\
    0.45
    पूर्ण
    0.45
    闶
    0.45
    後の
    0.44
    itabbo
    0.44
    綘
    0.44
    POSITIVE LOGITS
    ↵
    0.52
     drain
    0.52
     =
    0.51
     micron
    0.51
     spawned
    0.49
     sieve
    0.48
     craze
    0.48
    حث
    0.47
     iron
    0.47
     runway
    0.46
    Activations Density 0.012%

    No Known Activations