© 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. 30442
    Prev
    Next
    INDEX
    Explanations

    mathematical parameters and greek letters

    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
     буквально
    -0.88
    pondi
    -0.85
    нула
    -0.84
    剰
    -0.81
    كذا
    -0.79
    全民
    -0.77
    🛶
    -0.77
    MINUS
    -0.76
     Motta
    -0.75
    Another
    -0.74
    POSITIVE LOGITS
    lambda
    1.00
    tau
    0.99
    parameter
    0.96
     parameter
    0.96
    alpha
    0.94
     λ
    0.94
     parameters
    0.93
     передний
    0.89
     alpha
    0.89
     Parameter
    0.88
    Activations Density 0.076%

    No Known Activations