© 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. 32732
    Prev
    Next
    INDEX
    Explanations

    Q: or DESCRIPTION:

    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
    Negative Logits
    ilerin
    -1.13
    〜。
    -1.13
    Dlaczego
    -1.13
    เพลง
    -1.12
     Divulgação
    -1.11
    ～。
    -1.09
    ФОР
    -1.09
    ಱ
    -1.08
     лак
    -1.08
     diagrama
    -1.08
    POSITIVE LOGITS
    割と
    1.20
     ensuing
    1.15
    ほとん
    1.14
     추가
    1.13
    そも
    1.13
    つづく
    1.12
     모든
    1.11
    為に
    1.11
    雰囲
    1.10
    Prezzo
    1.10
    Activations Density 0.000%

    No Known Activations