© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84672
    Prev
    Next
    INDEX
    Explanations

    properties following its/their

    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
    öffnung
    -1.70
    vertreter
    -1.69
    llten
    -1.69
    cketed
    -1.61
    chers
    -1.60
    vereignty
    -1.59
     Поэтому
    -1.59
    
    -1.55
    istani
    -1.55
    itisation
    -1.54
    POSITIVE LOGITS
     many
    1.91
      
    1.70
     effect
    1.62
    ]
    1.60
    -
    1.52
     we
    1.51
    聾
    1.49
     probably
    1.47
     its
    1.46
     has
    1.45
    Activations Density 0.081%

    No Known Activations