© 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. 22-GEMMASCOPE-RES-131K
    7. 69283
    Prev
    Next
    INDEX
    Explanations

    adverbs of sequence or manner

    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
     still
    -1.22
     unusually
    -1.20
     if
    -1.20
     oddly
    -1.19
     surprisingly
    -1.13
     continued
    -1.12
     strangely
    -1.09
     undeniably
    -1.09
     obviously
    -1.06
     arguably
    -1.05
    POSITIVE LOGITS
    both
    1.56
     både
    1.34
     zowel
    1.22
     ſont
    1.20
     both
    1.18
    ทั้ง
    1.17
     delectable
    1.16
     verschillende
    1.11
     tiek
    1.09
     sumptuous
    1.08
    Activations Density 0.043%

    No Known Activations