© 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. 13365
    Prev
    Next
    INDEX
    Explanations

    being, going, having, giving

    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
    や
    -1.58
     jego
    -1.48
    <bos>
    -1.41
    を
    -1.39
    によって
    -1.39
    で
    -1.38
    などを
    -1.36
    時間は
    -1.32
    だが
    -1.30
    行動
    -1.28
    POSITIVE LOGITS
    久し
    1.34
    づけ
    1.31
    必要があります
    1.30
    為に
    1.30
    を読む
    1.28
     It
    1.28
    様な
    1.27
    際には
    1.27
    こない
    1.27
    つづく
    1.25
    Activations Density 0.057%

    No Known Activations