© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8959
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and adverbs

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

    qualifying adjectives and adverbs

    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_40_width_16k_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
    ，
    0.94
    ،
    0.92
    .
    0.82
    、
    0.79
    。
    0.65
    ፣
    0.63
     ،
    0.62
    ၊
    0.61
    、「
    0.59
    ﹐
    0.58
    POSITIVE LOGITS
     illetve
    0.59
     odnosno
    0.59
     voire
    0.57
     którzy
    0.55
    あるいは
    0.55
    特别是
    0.53
     anzi
    0.53
     اتارنا
    0.50
     ktorí
    0.50
    屢
    0.50
    Activations Density 1.692%

    No Known Activations