© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13564
    Prev
    Next
    INDEX
    Explanations

    historical source or scientific citation

    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
    इ
    2.64
    ు
    2.64
    ゅ
    2.54
    ులు
    2.36
    槤
    2.34
    िप्स
    2.29
     lair
    2.28
    度に
    2.27
     пов
    2.26
    خواه
    2.25
    POSITIVE LOGITS
    edi
    2.54
    eden
    2.51
    ech
    2.27
    Master
    2.15
    MACHINE
    2.15
    𝗲
    2.12
    leness
    2.12
    artment
    2.08
    reno
    2.07
    lech
    2.07
    Activations Density 0.106%

    No Known Activations