© 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. 22-GEMMASCOPE-RES-131K
    7. 11041
    Prev
    Next
    INDEX
    Explanations

    why would this be different

    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_22/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
     carne
    -0.89
    gunas
    -0.83
    ISTO
    -0.81
    ARTA
    -0.79
     kanske
    -0.79
    сування
    -0.78
    ifice
    -0.76
    OURS
    -0.76
     довольно
    -0.76
    chise
    -0.75
    POSITIVE LOGITS
     continue
    1.39
     continues
    1.09
    continue
    1.09
    今回も
    1.02
     expect
    1.02
     will
    0.99
     continuing
    0.97
    continuing
    0.95
    继续
    0.89
     same
    0.88
    Activations Density 0.019%

    No Known Activations