© 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. 34-GEMMASCOPE-RES-131K
    7. 63734
    Prev
    Next
    INDEX
    Explanations

    technical tests and studies

    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
     chrétien
    -0.83
     sguardo
    -0.79
     に関する
    -0.77
    phate
    -0.76
     posible
    -0.75
    قل
    -0.75
    ######
    -0.74
    ➭
    -0.73
     cristiano
    -0.73
    сят
    -0.71
    POSITIVE LOGITS
    QByteArray
    0.87
     Righ
    0.85
     試験
    0.84
    Mnemonic
    0.84
     FUL
    0.84
    adop
    0.80
     иссле
    0.79
     Eraser
    0.78
     test
    0.77
     accessories
    0.76
    Activations Density 0.089%

    No Known Activations