© 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. 29901
    Prev
    Next
    INDEX
    Explanations

    dividing into two parts

    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
     of
    -1.21
     entire
    -0.99
        
    -0.92
    他是
    -0.89
     gesamte
    -0.87
     ganze
    -0.86
     both
    -0.85
     dingen
    -0.84
     item
    -0.81
     łą
    -0.79
    POSITIVE LOGITS
     parts
    1.81
     separate
    1.68
     smaller
    1.67
     seperate
    1.44
    separate
    1.41
     halves
    1.37
     частей
    1.35
     terpisah
    1.34
     části
    1.34
    parts
    1.32
    Activations Density 0.086%

    No Known Activations