© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99662
    Prev
    Next
    INDEX
    Explanations

    adverb intensity and specific endings

    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_10/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
     Those
    -3.23
    Those
    -3.06
    With
    -2.98
     bringing
    -2.95
     longstanding
    -2.94
     giving
    -2.91
     providing
    -2.89
     Surprisingly
    -2.88
     dazzling
    -2.86
     Since
    -2.83
    POSITIVE LOGITS
     insanely
    3.58
    轳
    3.42
     revamped
    3.42
     ridiculously
    3.38
    艄
    3.34
     unbelievably
    3.31
     amazingly
    3.22
     delightfully
    3.14
     wonderfully
    3.13
     dismal
    3.13
    Activations Density 0.011%

    No Known Activations