© 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. 16-GEMMASCOPE-2-RES-16K
    7. 45
    Prev
    Next
    INDEX
    Explanations

    learning and training topics

    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_16_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
    ی
    0.57
    یتی
    0.43
    ﺮ
    0.42
    ۹
    0.41
    ۴
    0.41
    ﻄ
    0.40
    ﺘ
    0.40
    rho
    0.39
    ᱕
    0.39
    ों
    0.39
    POSITIVE LOGITS
     as
    0.50
    ar
    0.45
     a
    0.44
    ,
    0.40
    बर्ग
    0.39
    é
    0.37
    ust
    0.36
     Using
    0.36
    ↵↵
    0.36
     remixes
    0.36
    Activations Density 5.350%

    No Known Activations