© 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. 11587
    Prev
    Next
    INDEX
    Explanations

    file paths and examples

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

    text explanation

    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
     আটক
    0.42
    魔法
    0.41
    ވަ
    0.41
    还
    0.40
     célèbre
    0.40
     traitement
    0.40
     océ
    0.39
     ВС
    0.39
    রণ
    0.39
     stai
    0.39
    POSITIVE LOGITS
    documentclass
    0.45
    年も
    0.43
    u
    0.41
    uxxxx
    0.41
    sides
    0.39
    reducer
    0.39
    sdale
    0.39
    ESOME
    0.38
    r
    0.38
     जिनकी
    0.38
    Activations Density 0.025%

    No Known Activations