© 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. 48517
    Prev
    Next
    INDEX
    Explanations

    for following words

    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
    зади
    -1.38
    moiselle
    -1.25
    lores
    -1.23
    ต่างๆ
    -1.23
    lewati
    -1.19
    hever
    -1.18
     dalamnya
    -1.18
     olika
    -1.17
    antwortung
    -1.16
     cómics
    -1.16
    POSITIVE LOGITS
     more
    2.11
     those
    2.06
     example
    2.00
     this
    1.86
     most
    1.84
    cing
    1.80
     further
    1.70
     each
    1.62
     some
    1.59
     many
    1.52
    Activations Density 0.057%

    No Known Activations