© 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. 102848
    Prev
    Next
    INDEX
    Explanations

    #include "file.h"

    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
     like
    -1.27
     by
    -1.20
     just
    -0.96
     at
    -0.91
     remain
    -0.88
    秋季
    -0.88
     any
    -0.86
     what
    -0.86
     so
    -0.86
     almost
    -0.86
    POSITIVE LOGITS
     которые
    0.90
     tinha
    0.90
     Kanna
    0.89
    kontrolle
    0.89
     которых
    0.87
     этих
    0.86
     mirroring
    0.86
     Hours
    0.86
    пления
    0.86
     exhilarating
    0.84
    Activations Density 0.016%

    No Known Activations