© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2882
    Prev
    Next
    INDEX
    Explanations

    code, natural language elements, non-english script

    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_7_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
     Мне
    1.83
    JU
    1.77
     (…)
    1.75
     Функ
    1.72
     Oka
    1.71
     Ти
    1.70
     Обе
    1.70
    Ж
    1.65
    죽
    1.64
     至
    1.64
    POSITIVE LOGITS
    lly
    2.23
    lty
    2.21
    parency
    2.00
    rary
    1.94
    ારે
    1.88
    δήποτε
    1.88
    ऩे
    1.87
    rte
    1.85
    ท์
    1.83
     গ্রহন
    1.80
    Activations Density 0.646%

    No Known Activations