© 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. 3399
    Prev
    Next
    INDEX
    Explanations

    titles and honored roles

    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
    journalist
    -0.94
    maiden
    -0.90
    Reporte
    -0.87
     décrire
    -0.85
    serving
    -0.85
    Receta
    -0.85
     présentent
    -0.84
    Journalist
    -0.83
    genicity
    -0.83
    lında
    -0.82
    POSITIVE LOGITS
     leader
    1.25
     founder
    1.13
     guide
    1.11
     great
    1.09
     friend
    1.08
     teacher
    1.06
     rescu
    1.03
     reve
    1.00
     father
    0.99
     wise
    0.98
    Activations Density 0.033%

    No Known Activations