© 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. 115837
    Prev
    Next
    INDEX
    Explanations

    subtraction and sequences

    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
    [++
    -1.13
    >+</
    -0.97
    +*
    -0.95
    ++
    -0.91
     sonra
    -0.87
    ⬆
    -0.87
     *++
    -0.84
    +
    -0.84
    eses
    -0.84
    ctory
    -0.81
    POSITIVE LOGITS
    subtract
    1.07
    [--
    1.06
     yesterday
    1.04
    ลด
    1.00
     предыду
    0.99
     reduced
    0.98
     мень
    0.97
     giảm
    0.94
     умень
    0.92
     меньше
    0.92
    Activations Density 0.022%

    No Known Activations