© 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. 30951
    Prev
    Next
    INDEX
    Explanations

    initialisms and foreign place names

    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
     Couple
    -0.82
    ák
    -0.75
     Wife
    -0.71
     commemoration
    -0.71
     большим
    -0.71
     نکته
    -0.71
     poniżej
    -0.71
    amante
    -0.70
     gòn
    -0.66
    van
    -0.66
    POSITIVE LOGITS
     raisons
    0.90
    whole
    0.89
    Демографія
    0.88
    either
    0.85
    עת
    0.84
     kacang
    0.83
    irtschaft
    0.81
     decidedly
    0.80
    balloon
    0.79
    カイブ
    0.79
    Activations Density 0.042%

    No Known Activations