© 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. 34-GEMMASCOPE-RES-131K
    7. 25915
    Prev
    Next
    INDEX
    Explanations

    verbs followed by by

    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_34/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
    在
    -1.23
    BY
    -1.16
    จาก
    -1.09
    ใน
    -1.07
    FROM
    -1.06
     في
    -1.05
    在大
    -1.03
    對
    -1.02
    เพื่อ
    -1.00
     در
    -0.98
    POSITIVE LOGITS
     by
    1.59
    자인
    1.02
    veste
    1.01
    歳の
    0.96
     basse
    0.96
    Ȼ
    0.95
    elope
    0.92
     vasi
    0.91
    COMES
    0.91
     llamados
    0.90
    Activations Density 0.178%

    No Known Activations