© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3132
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives and their context

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

    superlatives describing ways

    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_31_width_262k_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
     \
    0.34
     suure
    0.29
     uchun
    0.28
    Anche
    0.26
    २
    0.26
    増加
    0.25
     ~\
    0.25
    ப்பும்
    0.25
    很好
    0.25
    。
    0.25
    POSITIVE LOGITS
     imaginable
    0.43
    in
    0.43
    iest
    0.40
     nhất
    0.38
    最有
    0.36
    ที่สุด
    0.36
    est
    0.36
     happiest
    0.33
     coolest
    0.32
    បំផុត
    0.32
    Activations Density 0.459%

    No Known Activations