© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 879
    Prev
    Next
    INDEX
    Explanations

    version numbers and software licenses

    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
    คน
    -0.80
     Check
    -0.77
    甙
    -0.71
    传输
    -0.69
    音频
    -0.69
    Notation
    -0.68
    بدأ
    -0.68
    徐
    -0.67
    速
    -0.67
    тан
    -0.66
    POSITIVE LOGITS
     amarillas
    0.85
    ベッド
    0.75
     acides
    0.73
     robar
    0.72
     longtemps
    0.72
    
    0.72
     interpr
    0.71
    邀请
    0.69
    Ⓩ
    0.69
     Wiley
    0.69
    Activations Density 0.026%

    No Known Activations