© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107843
    Prev
    Next
    INDEX
    Explanations

    champion League or seeds

    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
    就没
    -1.03
     sharply
    -0.94
     замена
    -0.93
     denuncias
    -0.91
     большая
    -0.90
     investigar
    -0.88
     evenly
    -0.88
     instrumentos
    -0.88
    zwa
    -0.88
    逦
    -0.87
    POSITIVE LOGITS
    🏆
    1.34
    Maybe
    1.07
     bertahan
    1.05
    Many
    0.96
    Several
    0.96
    Ту
    0.96
     champ
    0.95
    стероид
    0.95
    pecia
    0.94
    Votre
    0.94
    Activations Density 0.014%

    No Known Activations