© 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. 2691
    Prev
    Next
    INDEX
    Explanations

    large quantities or frequent occurrences

    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
     ${(
    -1.23
     continuare
    -1.17
    appropriate
    -1.16
    があれば
    -1.16
     nyní
    -1.14
     pernic
    -1.13
    whatever
    -1.12
    合适的
    -1.11
     pouvons
    -1.09
     consegue
    -1.08
    POSITIVE LOGITS
     large
    2.38
     frequently
    1.99
    大量
    1.98
     lots
    1.93
     frequent
    1.90
     heavily
    1.69
     long
    1.64
     lot
    1.63
    需要
    1.62
     Lots
    1.61
    Activations Density 0.318%

    No Known Activations