© 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. 87014
    Prev
    Next
    INDEX
    Explanations

    X of Y constructions

    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
    вят
    -0.79
    性价比
    -0.78
    nieuw
    -0.77
     anpassen
    -0.77
    円で
    -0.76
    Màu
    -0.75
    싫
    -0.74
     Mirage
    -0.72
    LETTER
    -0.72
     absch
    -0.71
    POSITIVE LOGITS
     Light
    0.78
     FormData
    0.77
     soil
    0.77
    ziell
    0.75
    햇
    0.74
    endi
    0.73
     QName
    0.73
    گذار
    0.72
     Replacement
    0.71
     Instruction
    0.70
    Activations Density 0.014%

    No Known Activations