© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98176
    Prev
    Next
    INDEX
    Explanations

    method and func calls

    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
     têm
    -0.79
    արտ
    -0.78
    holo
    -0.77
     adecuadamente
    -0.76
    áce
    -0.75
     Estudios
    -0.73
    utnik
    -0.73
    imenti
    -0.72
    EVA
    -0.72
    ôts
    -0.72
    POSITIVE LOGITS
     a
    1.26
    a
    1.07
    method
    1.04
     metod
    0.97
     method
    0.93
     b
    0.92
     metodo
    0.92
     mo
    0.90
    mo
    0.89
    func
    0.86
    Activations Density 0.005%

    No Known Activations