© 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. 95372
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    ditionally
    -0.91
     nomenclature
    -0.91
     enää
    -0.91
     espere
    -0.88
    yil
    -0.87
    плі
    -0.84
    īm
    -0.84
    ungkin
    -0.84
    Shelter
    -0.82
    紬
    -0.79
    POSITIVE LOGITS
    놀
    0.97
    ционное
    0.96
    se
    0.82
    ţilor
    0.81
     endowed
    0.81
     سات
    0.81
    ということで
    0.81
    nym
    0.80
    総評
    0.80
    #%%
    0.79
    Activations Density 0.006%

    No Known Activations