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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77917
    Prev
    Next
    INDEX
    Explanations

    recent studies and advances

    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
     currently
    -1.73
     already
    -1.32
     presently
    -1.31
    сей
    -1.27
     later
    -1.23
    currently
    -1.23
     dnes
    -1.23
     huidige
    -1.23
     choses
    -1.17
    eventually
    -1.17
    POSITIVE LOGITS
     additions
    1.78
     developments
    1.77
     spate
    1.69
     graduates
    1.62
     addition
    1.60
     legislation
    1.50
     emphasis
    1.46
     history
    1.41
     advances
    1.41
     trends
    1.38
    Activations Density 0.035%

    No Known Activations