© 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. 3559
    Prev
    Next
    INDEX
    Explanations

    numbered lists or headings

    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
     both
    -0.92
    :@"
    -0.91
     pesta
    -0.88
     dirilis
    -0.87
     every
    -0.86
     APPELLANT
    -0.84
    🕊
    -0.83
    umeur
    -0.82
    ｎ
    -0.82
     started
    -0.81
    POSITIVE LOGITS
     LONG
    1.21
     justi
    1.06
     aiuta
    1.04
     embodi
    0.97
    Swar
    0.91
    sproz
    0.90
     imme
    0.88
     longs
    0.87
    ModelAdmin
    0.87
     expan
    0.86
    Activations Density 0.000%

    No Known Activations