© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103105
    Prev
    Next
    INDEX
    Explanations

    click here

    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
    Not in Any Lists

    No Comments

    Negative Logits
     many
    -1.01
     when
    -0.94
     häufig
    -0.91
     At
    -0.88
     As
    -0.84
     a
    -0.82
     UK
    -0.81
    理性
    -0.80
     C
    -0.80
     es
    -0.79
    POSITIVE LOGITS
     HERE
    1.66
     here
    1.64
     you
    1.41
     trouvera
    1.35
    here
    1.22
    HERE
    1.22
     clicking
    1.16
     можете
    1.13
     здесь
    1.13
     descobrir
    1.10
    Activations Density 0.020%

    No Known Activations