© 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. 141832
    Prev
    Next
    INDEX
    Explanations

    imperialism, sterilization, machines, browning

    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
    :
    0.71
    3
    0.64
    +
    0.57
    ).
    0.57
    )
    0.55
    0
    0.55
    '
    0.54
    );
    0.54
    ：
    0.53
    ):
    0.53
    POSITIVE LOGITS
    아요
    0.62
    이스
    0.61
    ătoare
    0.61
    𝐈
    0.60
     इस्तेमाल
    0.59
    وڈ
    0.59
     꿈
    0.59
     맥
    0.58
    ੀ
    0.58
    íny
    0.58
    Activations Density 0.000%

    No Known Activations