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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36397
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     niestety
    -1.08
    clé
    -1.06
    ようです
    -1.05
    んですが
    -0.97
     Find
    -0.96
    ingway
    -0.96
    پر
    -0.96
    Now
    -0.95
     Now
    -0.95
     Created
    -0.93
    POSITIVE LOGITS
     of
    1.72
     in
    1.55
     among
    1.45
     amongst
    1.20
    だからこそ
    1.17
     anyway
    1.05
    暇
    0.99
     who
    0.98
     anywhere
    0.97
     others
    0.96
    Activations Density 0.031%

    No Known Activations