© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 20014
    Prev
    Next
    INDEX
    Explanations

    specific terms in technical contexts

    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
    .
    0.69
    {
    0.63
     an
    0.61
     a
    0.59
    이었다
    0.57
    ).
    0.53
     
    0.49
     it
    0.49
    .)
    0.48
    )
    0.47
    POSITIVE LOGITS
     kinks
    0.55
     निर्देशों
    0.52
    šen
    0.51
     queues
    0.49
     nostre
    0.48
     Tregs
    0.47
    ឆ្ល
    0.47
     আশে
    0.46
     vanes
    0.46
    ؤ
    0.46
    Activations Density 0.040%

    No Known Activations