© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13634
    Prev
    Next
    INDEX
    Explanations

    online products and services

    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
    為に
    -2.02
    ほら
    -1.88
    様な
    -1.64
    ようになります
    -1.57
    際には
    -1.56
    えっ
    -1.55
     wezen
    -1.53
    ところに
    -1.52
    のですか
    -1.52
    奬
    -1.51
    POSITIVE LOGITS
    などが
    1.80
    しかし
    1.79
    がありますが
    1.63
    結局
    1.59
    <0xA3>
    1.59
    がある
    1.57
    ですが
    1.57
    などは
    1.56
    <bos>
    1.55
    を
    1.52
    Activations Density 0.002%

    No Known Activations