© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 14527
    Prev
    Next
    INDEX
    Explanations

    Markdown links ending in https

    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
    𝘇
    2.31
    லாமல்
    1.98
     canh
    1.96
    Externe
    1.94
    තා
    1.90
    '>");
    1.87
    Trước
    1.87
     skoro
    1.85
    තාව
    1.83
    menubar
    1.82
    POSITIVE LOGITS
    ي
    2.60
    ोटो
    2.51
    ー
    2.16
    matical
    2.14
    י
    2.12
    يلا
    2.08
     Hear
    2.06
    сь
    2.04
    س
    2.03
    靼
    2.02
    Activations Density 0.001%

    No Known Activations