© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45529
    Prev
    Next
    INDEX
    Explanations

    umbrella devices and wipers

    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
    Negative Logits
    никам
    -1.30
    ributes
    -1.16
    飙
    -1.15
    嶸
    -1.13
    ageable
    -1.13
    ловой
    -1.12
    次回
    -1.11
    ribute
    -1.09
    February
    -1.09
    inness
    -1.09
    POSITIVE LOGITS
    Jeez
    1.19
    百分之
    1.18
    Shouldn
    1.15
     banged
    1.14
    Refrain
    1.11
    Academics
    1.10
    并将
    1.07
    Odour
    1.06
     partículas
    1.05
    大于
    1.05
    Activations Density 0.025%

    No Known Activations