© 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. 10-GEMMASCOPE-RES-131K
    7. 61193
    Prev
    Next
    INDEX
    Explanations

    technical code examples

    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_10/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
     this
    -1.67
     not
    -1.66
     to
    -1.59
    高的
    -1.41
     "
    -1.40
     last
    -1.34
    o
    -1.33
     इसकी
    -1.32
     that
    -1.23
     była
    -1.23
    POSITIVE LOGITS
     are
    2.13
    
    1.70
    Ꮀ
    1.59
     revive
    1.55
     wayward
    1.52
     protože
    1.52
     financiar
    1.51
    pectives
    1.49
    %">
    1.48
    を行う
    1.47
    Activations Density 0.005%

    No Known Activations