© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40715
    Prev
    Next
    INDEX
    Explanations

    personal opinions and involvement

    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
    虓
    -2.34
     If
    -2.30
    よい
    -2.22
    </h3>
    -2.09
    щики
    -2.08
     
    -2.06
     Because
    -2.06
     “
    -2.05
     veritable
    -2.03
    MockBean
    -2.02
    POSITIVE LOGITS
    椟
    2.64
     ragaz
    2.61
    
    2.58
    鹟
    2.56
     現貨
    2.45
     anun
    2.45
     rende
    2.44
     イラストレーション
    2.42
     ſch
    2.41
     تجه
    2.41
    Activations Density 0.002%

    No Known Activations