© 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. 1824
    Prev
    Next
    INDEX
    Explanations

    highly speak/think/opinion

    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
     أهم
    -0.79
     адре
    -0.76
     aange
    -0.75
    анти
    -0.72
    쁜
    -0.70
     judul
    -0.69
     welcomed
    -0.69
    係
    -0.68
    ulah
    -0.68
    жте
    -0.67
    POSITIVE LOGITS
     highly
    3.20
    highly
    2.89
    Highly
    2.83
     Highly
    2.69
     высоко
    1.98
     HIGH
    1.91
     altamente
    1.88
    HIGH
    1.87
     lowly
    1.73
     hig
    1.70
    Activations Density 0.019%

    No Known Activations