© 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. 60858
    Prev
    Next
    INDEX
    Explanations

    Zimbabwe, legislator, Jonathan

    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
     Indian
    -0.88
    ɛ
    -0.86
     or
    -0.86
    keyboardType
    -0.85
    REC
    -0.85
     Botswana
    -0.84
     motorists
    -0.84
     at
    -0.83
     cardinal
    -0.83
    odynamics
    -0.82
    POSITIVE LOGITS
     ſer
    1.09
     поддержка
    1.02
     持つ
    0.98
    arnya
    0.97
     gili
    0.96
     lais
    0.96
    ⽼
    0.91
     chúc
    0.91
     ステッカー
    0.91
     harap
    0.89
    Activations Density 0.008%

    No Known Activations