© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26375
    Prev
    Next
    INDEX
    Explanations

    code or technical identifiers

    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
    corrhi
    -1.70
    為に
    -1.63
    つづく
    -1.56
    の方に
    -1.50
    あー
    -1.48
    様な
    -1.47
    久し
    -1.46
    際に
    -1.41
     beeintr
    -1.41
    の方も
    -1.40
    POSITIVE LOGITS
    <bos>
    1.59
    參考資料
    1.37
     Grüßen
    1.33
    と
    1.26
    態度
    1.25
     sämtliche
    1.23
    そのため
    1.23
    <0xA3>
    1.23
    參考文獻
    1.20
    捗
    1.18
    Activations Density 0.061%

    No Known Activations