© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34811
    Prev
    Next
    INDEX
    Explanations

    options formula

    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
    cobacterium
    -1.52
    を行い
    -1.41
    場合には
    -1.39
    に使用
    -1.38
    えっ
    -1.31
    ほら
    -1.31
    ísmo
    -1.30
    あー
    -1.29
    こともあり
    -1.28
    事が
    -1.27
    POSITIVE LOGITS
    <bos>
    1.77
     still
    1.53
    では
    1.38
     nochmals
    1.33
     with
    1.30
    5
    1.28
    しかし
    1.27
    は
    1.25
     for
    1.25
    もちゃ
    1.24
    Activations Density 0.001%

    No Known Activations