© 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. 65152
    Prev
    Next
    INDEX
    Explanations

    make it even easier

    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
     which
    -1.52
     what
    -1.41
     using
    -1.40
     striving
    -1.39
     having
    -1.32
     definitely
    -1.30
    肇
    -1.30
    ᴇ
    -1.30
     where
    -1.29
    ：@
    -1.29
    POSITIVE LOGITS
     Wirksamkeit
    1.55
     Auffassung
    1.50
     EVEN
    1.48
    </b>
    1.40
    ひた
    1.38
     adorned
    1.37
     Belastung
    1.37
     cuando
    1.37
    凊
    1.33
     nawet
    1.32
    Activations Density 0.031%

    No Known Activations