© 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. 73950
    Prev
    Next
    INDEX
    Explanations

    based on condition

    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
    曲は
    -1.57
    を
    -1.36
    や
    -1.34
    搅拌
    -1.25
    轍
    -1.24
    ～♪
    -1.23
    で
    -1.22
    文獻
    -1.22
    資料來源
    -1.20
    もあって
    -1.20
    POSITIVE LOGITS
    為に
    1.75
    ほら
    1.48
    ええ
    1.46
    ヤバ
    1.46
    ようで
    1.45
    ところに
    1.44
     their
    1.43
    久し
    1.40
    ままで
    1.38
    様な
    1.34
    Activations Density 0.073%

    No Known Activations