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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11418
    Prev
    Next
    INDEX
    Explanations

    decay, decline, fading

    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
     citroen
    -1.35
    還會
    -1.34
    阗
    -1.33
    屢
    -1.30
    一辈子
    -1.29
    楽しく
    -1.28
     oreilles
    -1.27
    baine
    -1.27
    總是
    -1.27
    目錄
    -1.23
    POSITIVE LOGITS
    ’
    1.50
     in
    1.43
     rapidly
    1.33
     from
    1.25
     slowly
    1.24
     gradually
    1.23
     
    1.20
     мора
    1.19
     decay
    1.15
     on
    1.14
    Activations Density 0.056%

    No Known Activations