© 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. 60115
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    aménagement
    -1.00
    ようになる
    -0.98
     løpet
    -0.97
    wählen
    -0.96
    taya
    -0.92
    şağı
    -0.90
    ianum
    -0.87
    knows
    -0.85
     达
    -0.85
    nok
    -0.85
    POSITIVE LOGITS
    "><
    0.98
    '><
    0.85
    ><
    0.85
    ണ്
    0.83
    今では
    0.75
     could
    0.74
     anatomic
    0.73
    現在は
    0.71
     |
    0.70
     sasa
    0.69
    Activations Density 0.006%

    No Known Activations