© 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. 82722
    Prev
    Next
    INDEX
    Explanations

    provided that licensed under

    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
     tackle
    -0.82
    halter
    -0.78
     tackled
    -0.78
    entes
    -0.77
    سياسي
    -0.77
     conocer
    -0.77
    ぜひ
    -0.74
    ător
    -0.74
    chromatic
    -0.73
     affecting
    -0.72
    POSITIVE LOGITS
     Flexible
    0.93
     cloves
    0.82
    ówka
    0.82
     parody
    0.77
     unidade
    0.77
    flexible
    0.77
    ánk
    0.76
    oinette
    0.76
     cumbre
    0.75
     flexible
    0.75
    Activations Density 0.001%

    No Known Activations