© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99797
    Prev
    Next
    INDEX
    Explanations

    ML grid positions

    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
    eltjes
    -0.96
     viewDid
    -0.90
     табле
    -0.90
    wellen
    -0.90
     ország
    -0.89
     Главная
    -0.89
     vaš
    -0.88
    Hips
    -0.88
    Shoes
    -0.87
    Ольга
    -0.87
    POSITIVE LOGITS
     adjacent
    1.36
     left
    1.23
     neighbouring
    1.13
     direction
    1.12
     neighbour
    1.10
     передний
    1.07
     neighbors
    1.05
     Left
    1.02
     West
    1.02
     neighbor
    1.01
    Activations Density 0.004%

    No Known Activations