© 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. 34-GEMMASCOPE-RES-131K
    4. 38320
    Prev
    Next
    INDEX
    Explanations

    XML schema instance qualifier

    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
     BERT
    -0.86
     Timor
    -0.82
    Cur
    -0.82
     tirelessly
    -0.78
     ORA
    -0.77
     CIN
    -0.76
    ikian
    -0.74
    ɟ
    -0.73
     INTE
    -0.72
    lifestyle
    -0.72
    POSITIVE LOGITS
     sizeof
    1.37
    sizeof
    1.23
     size
    1.12
    **/
    
    0.94
     Size
    0.91
     Weight
    0.88
     Calculate
    0.86
    ましい
    0.86
     tamaño
    0.86
    size
    0.84
    Activations Density 0.001%

    No Known Activations