© 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. 34-GEMMASCOPE-RES-131K
    7. 107305
    Prev
    Next
    INDEX
    Explanations

    cru, cruise, cruel, crucial

    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_34/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
     Occasionally
    -1.13
     transgress
    -1.05
     هناك
    -1.02
    についての
    -1.01
     concreta
    -0.98
    就算是
    -0.97
    還會
    -0.96
    種類の
    -0.96
     Eventually
    -0.94
     功能
    -0.94
    POSITIVE LOGITS
     cru
    1.43
    Cru
    1.41
     Cru
    1.41
     CRU
    1.14
     Cruise
    1.13
     Кру
    1.03
     CR
    0.99
     cruising
    0.99
    姓名
    0.97
    cru
    0.96
    Activations Density 0.018%

    No Known Activations