© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25195
    Prev
    Next
    INDEX
    Explanations

    after he

    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
    或者
    -1.24
    或
    -1.19
    或是
    -1.16
    所で
    -1.05
     или
    -1.05
     henne
    -1.05
    جموعة
    -1.04
     schrijven
    -1.04
    <h1>
    -1.01
    ＊＊＊＊
    -1.01
    POSITIVE LOGITS
    东京
    1.10
    视为
    1.06
     later
    1.05
     after
    1.05
    与此同时
    1.02
    良いです
    1.02
     he
    0.96
    馳走
    0.91
     לאחר
    0.91
     बाद
    0.90
    Activations Density 0.030%

    No Known Activations