© 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. 22-GEMMASCOPE-RES-131K
    7. 15021
    Prev
    Next
    INDEX
    Explanations

    shapes in numerical contexts

    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_22/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
     Those
    -1.26
     only
    -1.15
     try
    -1.13
     enough
    -1.13
     tries
    -1.12
     during
    -1.09
     if
    -1.08
     after
    -1.05
     before
    -1.03
    -1.02
    POSITIVE LOGITS
     actrice
    1.18
    趿
    1.13
     إنتاج
    1.09
    两个人
    1.09
    issent
    1.09
    attached
    1.08
    normally
    1.08
    تاریخ
    1.07
    ánea
    1.06
     môžu
    1.06
    Activations Density 0.003%

    No Known Activations