© 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. 90570
    Prev
    Next
    INDEX
    Explanations

    Semiconductor feasibility Xen

    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
    entiment
    -0.77
     geschaffen
    -0.76
    roffene
    -0.74
     abordar
    -0.73
    mjs
    -0.73
    couvrez
    -0.72
    壽司
    -0.70
     MEA
    -0.69
     tòa
    -0.69
    NumberOf
    -0.69
    POSITIVE LOGITS
     Xen
    0.95
    Xen
    0.91
    Phrase
    0.88
     võimal
    0.83
     XF
    0.82
    RICIA
    0.82
    xen
    0.82
    ক্ত
    0.79
    xf
    0.78
     Alban
    0.77
    Activations Density 0.011%

    No Known Activations