© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70050
    Prev
    Next
    INDEX
    Explanations

    software modules

    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
    侂
    -2.36
     The
    -2.23
     This
    -2.23
    i
    -2.17
     ของ
    -2.17
     '
    -2.13
    一個
    -1.98
     Of
    -1.98
    鼉
    -1.97
    
    -1.88
    POSITIVE LOGITS
    providedIn
    2.88
    </h6>
    2.67
    modules
    2.66
    </sub>
    2.64
    </h3>
    2.31
     تعدى
    2.22
    д
    2.14
    觔
    2.14
    巿
    2.11
    ”،
    2.08
    Activations Density 0.006%

    No Known Activations