© 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. 53841
    Prev
    Next
    INDEX
    Explanations

    preventing or improving

    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
     mulher
    -0.75
    裨
    -0.73
     maybe
    -0.73
     Просто
    -0.72
     крити
    -0.70
    下了
    -0.69
     обществе
    -0.69
     皿
    -0.69
    我了
    -0.69
    Radio
    -0.68
    POSITIVE LOGITS
    Terminate
    0.85
    йте
    0.85
     />;
    0.82
     Mozilla
    0.82
    ","","
    0.81
     banknotes
    0.81
     PUP
    0.81
     bekym
    0.81
    FormTagHelper
    0.81
     Lockheed
    0.80
    Activations Density 0.001%

    No Known Activations