© 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. 8102
    Prev
    Next
    INDEX
    Explanations

    forced or necessitated actions

    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
    ."
    -1.68
     not
    -1.58
     only
    -1.54
    tileno
    -1.48
     at
    -1.44
     
    -1.41
     methods
    -1.41
     is
    -1.38
     seems
    -1.37
     appears
    -1.37
    POSITIVE LOGITS
     egna
    1.63
    b
    1.58
     motoru
    1.57
     小物
    1.56
     brachten
    1.54
     sám
    1.48
    ⇕
    1.47
     ถ้า
    1.45
    7
    1.45
    ወ
    1.45
    Activations Density 0.048%

    No Known Activations