© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71092
    Prev
    Next
    INDEX
    Explanations

    academic degrees

    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_10/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
    すじ
    -1.35
     their
    -1.35
     dugaan
    -1.34
    好啊
    -1.33
    »,
    -1.33
     které
    -1.32
    笮
    -1.32
     each
    -1.32
     dhe
    -1.32
     passe
    -1.31
    POSITIVE LOGITS
    4
    1.59
    2
    1.45
    höhung
    1.34
     Verbrechen
    1.34
    ího
    1.33
     underwhelming
    1.32
     degree
    1.30
     ベクトル
    1.29
    であった
    1.26
     Anliegen
    1.26
    Activations Density 0.059%

    No Known Activations