© 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. 11512
    Prev
    Next
    INDEX
    Explanations

    container ship or runtime

    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
    с
    1.21
    は
    1.13
    은
    1.01
    在
    1.00
    ス
    0.97
    ますが
    0.96
    도
    0.95
    ও
    0.91
    ονται
    0.88
    ри
    0.87
    POSITIVE LOGITS
    at
    1.35
    il
    1.20
     for
    1.10
    ag
    1.03
    la
    1.03
    and
    1.02
    w
    1.02
    x
    1.02
    n
    1.00
     Containers
    1.00
    Activations Density 0.007%

    No Known Activations