© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94226
    Prev
    Next
    INDEX
    Explanations

    events and transitions

    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
    Negative Logits
    Obviously
    -0.97
    The
    -0.96
    It
    -0.96
    However
    -0.93
    Another
    -0.91
    Their
    -0.91
    Luckily
    -0.88
    Surprisingly
    -0.88
    Does
    -0.88
    Unfortunately
    -0.88
    POSITIVE LOGITS
    UREAU
    1.07
    cenario
    1.07
     procedure
    1.05
     mechanism
    1.05
    Mechanism
    1.02
     happening
    1.01
    方式
    0.97
     occurs
    0.96
     prosedur
    0.96
     joya
    0.95
    Activations Density 0.069%

    No Known Activations