© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13413
    Prev
    Next
    INDEX
    Explanations

    for aliens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     languages
    1.23
     মজুমদার
    1.16
    符
    1.15
    作文
    1.15
     id
    1.11
     SAP
    1.09
     Languages
    1.09
    tras
    1.07
    ).(
    1.07
    Recognizer
    1.07
    POSITIVE LOGITS
    ディスプレイ
    1.45
    omist
    1.37
    ぎ
    1.35
    orne
    1.35
    ГА
    1.34
    riendo
    1.32
    рёх
    1.32
     двадцать
    1.30
    賑
    1.29
    rägt
    1.29
    Activations Density 0.000%

    No Known Activations