© 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. 34-GEMMASCOPE-RES-131K
    7. 29962
    Prev
    Next
    INDEX
    Explanations

    our collective references

    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
    Negative Logits
     apparently
    -1.05
     hombre
    -0.95
     their
    -0.92
    🎣
    -0.91
     Apparently
    -0.91
    жд
    -0.88
     reportedly
    -0.87
     worden
    -0.87
     	e
    -0.87
    👩
    -0.86
    POSITIVE LOGITS
     our
    1.51
     unserer
    1.27
     nosso
    1.20
     unseres
    1.16
     nossos
    1.16
     нашей
    1.16
     нашего
    1.14
     we
    1.12
     μας
    1.12
    我们
    1.09
    Activations Density 0.021%

    No Known Activations