© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3261
    Prev
    Next
    INDEX
    Explanations

    environment variables

    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
     Könige
    -0.86
    کنندگان
    -0.83
     vorigen
    -0.81
     إسرائيل
    -0.79
    արտ
    -0.79
    
    -0.79
    ธุ
    -0.78
     huu
    -0.78
    vangen
    -0.77
     दि
    -0.76
    POSITIVE LOGITS
    npm
    1.24
    REACT
    1.20
    ׃
    1.04
     NODE
    1.03
    NODE
    1.02
     comien
    0.89
     npm
    0.88
     React
    0.87
     línea
    0.87
     LT
    0.85
    Activations Density 0.004%

    No Known Activations