© 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. 116922
    Prev
    Next
    INDEX
    Explanations

    distribute

    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
    Steps
    -0.77
    copy
    -0.71
    Imagin
    -0.69
    aima
    -0.69
     Renner
    -0.68
     зарубе
    -0.68
     아이
    -0.68
    ngo
    -0.67
    Bk
    -0.67
    arankan
    -0.66
    POSITIVE LOGITS
    り
    0.68
    下降
    0.68
     водой
    0.67
     powierzchni
    0.67
     CBN
    0.67
    Lam
    0.65
     earrings
    0.65
    uzzy
    0.63
    كال
    0.63
     Honda
    0.62
    Activations Density 0.051%

    No Known Activations