© 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. 104474
    Prev
    Next
    INDEX
    Explanations

    transition, predecessor, rotational, refers

    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
     horror
    -0.91
     presidents
    -0.83
     adventure
    -0.81
     ($("#
    -0.81
     collaborative
    -0.79
     prayer
    -0.79
     entrepreneurs
    -0.79
     filmmaking
    -0.79
    Horror
    -0.79
     thriller
    -0.79
    POSITIVE LOGITS
     ámbito
    0.93
    excellents
    0.93
     magnified
    0.90
     localVar
    0.89
     OUTSIDE
    0.89
     przypadku
    0.88
     overseas
    0.88
    ―――
    0.86
    capulco
    0.86
    PHYSICAL
    0.85
    Activations Density 0.177%

    No Known Activations