© 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. 3250
    Prev
    Next
    INDEX
    Explanations

    tikz graphics

    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
     bahagian
    -1.05
     bagian
    -0.96
     or
    -0.95
     iyo
    -0.87
    carboxylic
    -0.86
     ▶
    -0.80
     and
    -0.80
    pygame
    -0.79
     >
    -0.79
    ...@
    -0.79
    POSITIVE LOGITS
    试试
    0.88
     Schedules
    0.86
    Gön
    0.86
     calitate
    0.86
    違い
    0.85
    ❫
    0.82
     नए
    0.81
    女
    0.81
     confort
    0.80
    作詞
    0.80
    Activations Density 0.001%

    No Known Activations