© 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
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2311
    Prev
    Next
    INDEX
    Explanations

    contrast words

    np_acts-logits-general · gemini-2.5-flash-lite

    but also or but not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сто
    0.44
    єю
    0.44
    یه
    0.43
    व
    0.42
     хоть
    0.41
    गें
    0.41
    ো
    0.40
    そして
    0.40
    {~
    0.39
    그리고
    0.39
    POSITIVE LOGITS
     nevertheless
    0.96
     nonetheless
    0.88
     dennoch
    0.73
     unfortunately
    0.73
     fortunately
    0.71
     retains
    0.70
     interestingly
    0.69
     néanmoins
    0.68
     luckily
    0.66
     তবুও
    0.66
    Activations Density 0.322%

    No Known Activations