© 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. 27898
    Prev
    Next
    INDEX
    Explanations

    numbers like 2 and 4

    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
     đỏ
    0.54
     它
    0.51
    يء
    0.49
     efficacement
    0.49
     specifiche
    0.49
     fitur
    0.48
     aiuta
    0.48
     দূর
    0.48
     யார்
    0.47
     不要
    0.47
    POSITIVE LOGITS
    st
    0.77
    К
    0.73
    전
    0.70
    Ц
    0.70
    )
    0.68
    ),
    0.68
    _
    0.68
    Б
    0.67
    Ни
    0.65
    n
    0.63
    Activations Density 0.001%

    No Known Activations