© 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. 40-GEMMASCOPE-2-RES-262K
    4. 29705
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions ("but")

    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_40_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
    ،
    0.98
    、
    0.89
    ,
    0.80
    ፣
    0.79
    ၊
    0.76
    ,
    0.70
    、「
    0.65
     ,
    0.63
    ),
    0.62
     、
    0.59
    POSITIVE LOGITS
     mutta
    0.75
     bukanlah
    0.62
     მაგრამ
    0.56
     sondern
    0.55
     लेकिन
    0.55
     lakini
    0.54
    s
    0.49
     pero
    0.49
     tačiau
    0.48
     ngunit
    0.48
    Activations Density 0.011%

    No Known Activations