© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67038
    Prev
    Next
    INDEX
    Explanations

    official approvals and sessions

    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
     they
    -1.45
     ilustrasi
    -1.40
    냑
    -1.35
     kark
    -1.30
     MÉXICO
    -1.27
    ẳn
    -1.27
    푠
    -1.27
     abstrak
    -1.27
    以上です
    -1.25
    を目指す
    -1.23
    POSITIVE LOGITS
    </em>
    1.51
    ."
    1.32
     r
    1.32
     all
    1.28
     jedynie
    1.27
     well
    1.23
     gdyż
    1.23
    mannian
    1.23
     Not
    1.23
     only
    1.20
    Activations Density 0.020%

    No Known Activations