© 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. 34-GEMMASCOPE-RES-131K
    7. 48922
    Prev
    Next
    INDEX
    Explanations

    programming languages and data formats

    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
     quienes
    -0.90
    jíma
    -0.82
     of
    -0.81
     كذلك
    -0.81
     bzw
    -0.80
     też
    -0.79
     πως
    -0.79
     htt
    -0.79
     كافة
    -0.79
    -...
    -0.79
    POSITIVE LOGITS
     you
    1.72
     although
    1.20
     therefore
    1.03
     despite
    0.96
     this
    0.93
     youll
    0.92
     potrebbe
    0.91
     pouvez
    0.91
    こんなに
    0.90
    {$
    0.90
    Activations Density 0.006%

    No Known Activations