© 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. 31-GEMMASCOPE-2-RES-16K
    7. 16262
    Prev
    Next
    INDEX
    Explanations

    scientific terms and measurements

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

    verb followed by preposition/participle

    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_31_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
    나
    0.39
    ల్‌
    0.38
    如下
    0.36
    CG
    0.36
    кий
    0.35
    ל
    0.34
    도
    0.34
    এস
    0.34
    াজ
    0.33
    ΟΥ
    0.33
    POSITIVE LOGITS
     trá
    0.36
     indignant
    0.34
     ഒന്ന
    0.33
     subjug
    0.32
     apparence
    0.32
     Jangan
    0.31
     lembut
    0.31
     annak
    0.31
     emociones
    0.30
     kusal
    0.30
    Activations Density 0.023%

    No Known Activations