© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123859
    Prev
    Next
    INDEX
    Explanations

    EEPROM, Enriched Environment, Enterprise Edition

    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_10/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
     “
    -3.00
     he
    -2.69
    </b>
    -2.64
     {
    -2.56
     большого
    -2.34
    笵
    -2.20
     essa
    -2.13
     mere
    -2.06
    完全に
    -2.05
    といえば
    -2.05
    POSITIVE LOGITS
    </h3>
    2.81
    \{
    2.11
    🌸
    2.09
    😳
    2.09
    😫
    2.03
    🙌
    1.98
     clandestine
    1.98
     $=$
    1.94
    鹮
    1.93
     questionSearch
    1.92
    Activations Density 0.005%

    No Known Activations