© 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. 29959
    Prev
    Next
    INDEX
    Explanations

    season opening and ending

    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
     periode
    -0.98
    mability
    -0.85
    ASKET
    -0.84
     период
    -0.83
    angered
    -0.82
    🉑
    -0.79
    ooze
    -0.79
    eness
    -0.77
    period
    -0.77
     Waterman
    -0.76
    POSITIVE LOGITS
     opener
    1.16
     ending
    1.06
     finale
    0.96
     defining
    0.93
     Opener
    0.91
     ender
    0.91
     preview
    0.84
    ending
    0.82
    訝
    0.81
    opener
    0.79
    Activations Density 0.029%

    No Known Activations