© 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. 25072
    Prev
    Next
    INDEX
    Explanations

    little followed by nouns

    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
    ﮑ
    -2.66
    lgari
    -2.50
     tissu
    -2.28
    镦
    -2.28
    
    -2.27
    嗫
    -2.23
    岜
    -2.23
     poussière
    -2.22
     ufe
    -2.19
    
    -2.17
    POSITIVE LOGITS
     For
    3.16
     для
    2.86
     Our
    2.77
     }],
    2.67
     Using
    2.67
     voor
    2.59
     „
    2.42
    ,“
    2.42
     That
    2.39
     }),
    2.39
    Activations Density 0.023%

    No Known Activations