© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117043
    Prev
    Next
    INDEX
    Explanations

    avoid repeated actions

    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
     любые
    -1.27
     любого
    -1.27
     einiger
    -1.23
     любой
    -1.18
    Whatever
    -1.18
     sembler
    -1.13
     любы
    -1.11
    whatever
    -1.09
     даже
    -1.09
    without
    -1.04
    POSITIVE LOGITS
     every
    2.13
     everytime
    2.00
     each
    1.97
     anymore
    1.63
     fiecare
    1.45
     chaque
    1.40
     cumbersome
    1.34
    毎回
    1.34
     каждый
    1.29
     hver
    1.27
    Activations Density 0.205%

    No Known Activations