© 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. 75048
    Prev
    Next
    INDEX
    Explanations

    whilst followed by diverse phrases

    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
    尴
    -2.78
     We
    -2.41
    𓂅
    -2.33
     我们
    -2.28
     внимательно
    -2.23
    仂
    -2.16
    醅
    -2.14
     нашу
    -2.14
    砗
    -2.14
    uminazione
    -2.06
    POSITIVE LOGITS
    ’
    2.97
    $
    2.89
    榈
    2.83
    ꔹ
    2.53
     Then
    2.50
    '
    2.44
    while
    2.41
    鹉
    2.36
    риях
    2.34
    I
    2.34
    Activations Density 0.003%

    No Known Activations