© 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. 22-GEMMASCOPE-RES-131K
    7. 16568
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    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
    Negative Logits
    薷
    -1.05
    нс
    -0.96
    的服务
    -0.96
    ⎡
    -0.95
     RANGE
    -0.94
    薬品
    -0.93
    otheses
    -0.92
    МС
    -0.92
    HBox
    -0.91
     Dé
    -0.91
    POSITIVE LOGITS
     and
    1.48
     with
    1.09
     further
    1.05
     changed
    1.03
    Modelos
    1.01
    Opel
    0.99
    Juven
    0.94
    还不错
    0.93
     that
    0.92
    cipta
    0.92
    Activations Density 0.001%

    No Known Activations