© 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. 103650
    Prev
    Next
    INDEX
    Explanations

    code and license headers

    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
    近
    -0.86
     close
    -0.76
    Estr
    -0.74
     te
    -0.71
     бли
    -0.71
     near
    -0.69
     gần
    -0.69
         
    -0.69
    atguigu
    -0.69
     withdrew
    -0.68
    POSITIVE LOGITS
     Mox
    0.86
     rapidamente
    0.84
    μαστε
    0.82
     Herzog
    0.77
    mittag
    0.77
    axaca
    0.75
    뜬
    0.75
     plc
    0.75
    fiehlt
    0.75
    lappe
    0.74
    Activations Density 0.001%

    No Known Activations