© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 72780
    Prev
    Next
    INDEX
    Explanations

    adverbs modifying descriptions

    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
    を
    -1.84
    がありますが
    -1.83
    と
    -1.70
    そして
    -1.66
    และ
    -1.66
    がある
    -1.55
    それにしても
    -1.52
     of
    -1.52
    ebly
    -1.49
    があり
    -1.48
    POSITIVE LOGITS
    為に
    1.91
    ところに
    1.64
     There
    1.45
    になりたい
    1.42
    に入れる
    1.42
    orkshire
    1.37
    ナメント
    1.36
     This
    1.34
     When
    1.34
     Then
    1.29
    Activations Density 0.096%

    No Known Activations