© 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-262K
    7. 3342
    Prev
    Next
    INDEX
    Explanations

    contrary conjunctions

    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_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
     boto
    0.42
     genotype
    0.38
     mime
    0.37
     KQkq
    0.36
     cents
    0.34
     async
    0.34
     detection
    0.34
     Ꭰ
    0.34
     genotypes
    0.33
     alpha
    0.33
    POSITIVE LOGITS
    只是
    1.04
    只不过
    0.90
     다만
    0.80
     เพียง
    0.77
    但是
    0.69
     പക്ഷേ
    0.64
     ولكن
    0.63
    但是在
    0.63
     ngunit
    0.62
     لیکن
    0.61
    Activations Density 0.251%

    No Known Activations