© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    code assignment and method calls

    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
     усилия
    -1.45
    ﾅ
    -1.41
    赑
    -1.36
     จาก
    -1.32
    Dougall
    -1.29
    viele
    -1.27
    according
    -1.27
     régiment
    -1.25
     potom
    -1.23
     toujours
    -1.22
    POSITIVE LOGITS
     that
    1.85
     their
    1.80
     they
    1.39
     it
    1.31
    -
    1.26
     вони
    1.23
     frischen
    1.23
     is
    1.20
    </u>
    1.18
     برانيه
    1.18
    Activations Density 0.005%

    No Known Activations