© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11634
    Prev
    Next
    INDEX
    Explanations

    punctuation and html tags

    np_acts-logits-general · gemini-2.5-flash-lite

    structured data snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дохода
    0.44
    Voltage
    0.40
    ADE
    0.40
    ステン
    0.40
    鲞
    0.40
    ствовал
    0.40
    шенные
    0.39
    Voice
    0.39
    စု
    0.39
    ArgumentParser
    0.39
    POSITIVE LOGITS
    <strong>
    0.48
     était
    0.44
     deverá
    0.44
    cliente
    0.43
     potrebbe
    0.43
     pouvait
    0.43
     avrebbe
    0.43
     sarebbe
    0.43
     sería
    0.42
    僥
    0.42
    Activations Density 0.026%

    No Known Activations