© 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. 32089
    Prev
    Next
    INDEX
    Explanations

    Hebrew and Arabic characters

    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
     this
    -2.17
     during
    -1.82
     ostensibly
    -1.76
     facilitates
    -1.74
     facilitating
    -1.74
     enables
    -1.69
     amidst
    -1.68
     cleverly
    -1.64
     began
    -1.63
     became
    -1.62
    POSITIVE LOGITS
     quintessential
    1.63
    ⏑
    1.61
     luscious
    1.61
     grumpy
    1.60
     tumultuous
    1.59
     ........
    1.52
     .......
    1.51
     cuatro
    1.48
     myriad
    1.47
     horrid
    1.47
    Activations Density 0.002%

    No Known Activations