© 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. 59917
    Prev
    Next
    INDEX
    Explanations

    academic degrees earned

    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
    郓
    -0.91
    ļa
    -0.89
    ḕ
    -0.88
     سوال
    -0.84
    BBA
    -0.84
    tritts
    -0.83
    ScrollBar
    -0.82
     hoteles
    -0.82
     Quarterly
    -0.80
    Bachelor
    -0.80
    POSITIVE LOGITS
     graduate
    2.13
     postgraduate
    2.09
     Masters
    2.06
     masters
    2.05
    Masters
    1.91
     master
    1.77
     grad
    1.66
     Master
    1.66
    masters
    1.66
     PhD
    1.63
    Activations Density 0.048%

    No Known Activations