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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90637
    Prev
    Next
    INDEX
    Explanations

    up, down, back movement followed by 'to'

    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
     out
    -1.17
    ができます
    -1.06
     that
    -1.05
     Aufenthalt
    -1.02
     over
    -1.02
    を行います
    -1.00
    UT
    -0.94
    をします
    -0.93
     dergleichen
    -0.93
    lanan
    -0.92
    POSITIVE LOGITS
     to
    1.29
    tadi
    0.97
    声優
    0.93
    vallis
    0.92
    koala
    0.90
     Bupati
    0.87
     histories
    0.86
    нове
    0.85
    פתח
    0.84
     fondament
    0.84
    Activations Density 0.035%

    No Known Activations